Benchmarks · /benchmarks/artificial-analysis-output-speed

Output Speed

Name: Output Speed
Creator: Artificial Analysis

Median output generation speed reported by Artificial Analysis.

Source · Artificial Analysis
Version · artificial-analysis snapshot 2026-06-24
Scores · 211

Test details

Visible tradeoffsThis is an efficiency signal, so it belongs beside quality rather than being mistaken for quality.

source

Artificial Analysis

metric

Tokens per second (tokens/s)

judge

Speed / cost

direction

higher better

group id

aa_output_speed_current

domain

Chat / text

What it measures vs what it misses

✓ Measures

Streaming output speed after generation begins.

✗ Misses

Answer quality and time spent reasoning before output starts.

Why this countsIt tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.Same-test ruleThis percentile only compares models inside the exact benchmark/version group shown here. It is not a universal score.What it missesIt does not prove deeper reasoning, tool use, or enterprise workflow reliability.

Leaderboard · this benchmark version

#1 · mercury-2

AA · Jun 24, 2026

Source label: Mercury 2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 100%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

978.6 tokens/s

#2 · LFM2 1.2B

AA · Jun 24, 2026

Source label: LFM2 1.2B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 99.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

555.4 tokens/s

#3 · LFM2.5-1.2B-Instruct

AA · Jun 24, 2026

Source label: LFM2.5-1.2B-Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 99%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

496.6 tokens/s

#4 · Granite 4.0 H Small

AA · Jun 24, 2026

Source label: Granite 4.0 H Small

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 98.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

453.9 tokens/s

#5 · LFM2.5-VL-1.6B

AA · Jun 24, 2026

Source label: LFM2.5-VL-1.6B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 98.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

442.4 tokens/s

#6 · Step 3.7 Flash

AA · Jun 24, 2026

Source label: Step 3.7 Flash

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 97.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

421.9 tokens/s

#7 · Gemini 3.1 Flash-Lite Preview

AA · Jun 24, 2026

Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 97.1%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

367.6 tokens/s

#8 · HyperNova 60B 2605

AA · Jun 24, 2026

Source label: HyperNova 60B 2605

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 96.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

367.5 tokens/s

#9 · Granite 3.3 8B (Non-reasoning)

AA · Jun 24, 2026

Source label: Granite 3.3 8B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 96.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

361.1 tokens/s

#10 · GPT-OSS 120B

AA · Jun 24, 2026

Source label: gpt-oss-120b (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 95.7%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

336.3 tokens/s

#11 · LFM2 2.6B

AA · Jun 24, 2026

Source label: LFM2 2.6B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 95.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

333.1 tokens/s

#12 · Nova Micro

AA · Jun 24, 2026

Source label: Nova Micro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 94.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

307.9 tokens/s

#13 · Nemotron 3 Nano Omni 30B A3B Reasoning

AA · Jun 24, 2026

Source label: Nemotron 3 Nano Omni 30B A3B Reasoning

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 94.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

275 tokens/s

#14 · Qwen3.5 Omni Flash

AA · Jun 24, 2026

Source label: Qwen3.5 Omni Flash

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 93.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

273.1 tokens/s

#15 · trinity-large-thinking

AA · Jun 24, 2026

Source label: Trinity Large Thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 93.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

253.4 tokens/s

#16 · Llama 3.1 Nemotron Instruct 70B

AA · Jun 24, 2026

Source label: Llama 3.1 Nemotron Instruct 70B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 92.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

247.6 tokens/s

#17 · minimax-m2.5

AA · Jun 24, 2026

Source label: MiniMax-M2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 92.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

242.5 tokens/s

#18 · Gemini 2.5 Flash-Lite

AA · Jun 24, 2026

Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 91.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

236 tokens/s

#19 · LFM2.5-8B-A1B

AA · Jun 24, 2026

Source label: LFM2.5-8B-A1B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 91.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

230.2 tokens/s

#20 · Gemini 2.5 Flash

AA · Jun 24, 2026

Source label: Gemini 2.5 Flash (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 91%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

228.7 tokens/s

#21 · Grok 4.20

AA · Jun 24, 2026

Source label: Grok 4.20 0309 v2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 90.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

226.5 tokens/s

#22 · MiniMax-M2.1

AA · Jun 24, 2026

Source label: MiniMax-M2.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 90%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

225.9 tokens/s

#23 · GPT-OSS 20B

AA · Jun 24, 2026

Source label: gpt-oss-20B (low)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 89.5%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

223.2 tokens/s

#24 · Grok 4.20 0309 (Non-reasoning)

AA · Jun 24, 2026

Source label: Grok 4.20 0309 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 89%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

213.2 tokens/s

#25 · NVIDIA Nemotron Nano 12B v2 VL (Reasoning)

AA · Jun 24, 2026

Source label: NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 88.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

211.2 tokens/s

#26 · nvidia-nemotron-3-super-120b-a12b

AA · Jun 24, 2026

Source label: NVIDIA Nemotron 3 Super 120B A12B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 88.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

211 tokens/s

#27 · step-3.5-flash

AA · Jun 24, 2026

Source label: Step 3.5 Flash 2603

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 87.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

207.2 tokens/s

#28 · Qwen3.7 Max

AA · Jun 24, 2026

Source label: Qwen3.7 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 87.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

201.9 tokens/s

#29 · Step 3.5 Flash

AA · Jun 24, 2026

Source label: Step 3.5 Flash

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 86.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

201.1 tokens/s

#30 · o3 mini

AA · Jun 24, 2026

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 86.2%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

197.8 tokens/s

#31 · Qwen3.6 35B A3B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3.6 35B A3B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 85.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

187.2 tokens/s

#32 · Gemini 3 Flash

AA · Jun 24, 2026

Source label: Gemini 3 Flash Preview (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 85.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

186.8 tokens/s

#33 · qwen3-next-80b-a3b-instruct

AA · Jun 24, 2026

Source label: Qwen3 Next 80B A3B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 84.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

183.6 tokens/s

#34 · Jamba 1.6 Mini

AA · Jun 24, 2026

Source label: Jamba 1.6 Mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 84.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

180 tokens/s

#35 · GPT-4.1 nano

AA · Jun 24, 2026

Source label: GPT-4.1 nano

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 83.8%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

179.6 tokens/s

#36 · Gemini 3.5 Flash

AA · Jun 24, 2026

Source label: Gemini 3.5 Flash (minimal)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

177.8 tokens/s

#37 · Mistral Small (Sep '24)

AA · Jun 24, 2026

Source label: Mistral Small (Sep '24)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 82.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

176.2 tokens/s

#38 · Qwen3.6 35B A3B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3.6 35B A3B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 82.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

175.9 tokens/s

#39 · Nova 2.0 Lite (low)

AA · Jun 24, 2026

Source label: Nova 2.0 Lite (low)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 81.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

172.7 tokens/s

#40 · Nova Lite

AA · Jun 24, 2026

Source label: Nova Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 81.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

172.2 tokens/s

#41 · o4 mini

AA · Jun 24, 2026

Source label: o4-mini (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 81%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

170.9 tokens/s

#42 · Qwen3 30B A3B 2507 Instruct

AA · Jun 24, 2026

Source label: Qwen3 30B A3B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 80.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

166.4 tokens/s

#43 · Mistral Small (Feb '24)

AA · Jun 24, 2026

Source label: Mistral Small (Feb '24)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 80%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

163.3 tokens/s

#44 · o3

AA · Jun 24, 2026

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 79.5%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

162.6 tokens/s

#45 · Nova 2.0 Lite (high)

AA · Jun 24, 2026

Source label: Nova 2.0 Lite (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 79%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

162.6 tokens/s

#46 · Qwen3.5 35B A3B

AA · Jun 24, 2026

Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 78.6%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

161.6 tokens/s

#47 · Mistral Small 3.1

AA · Jun 24, 2026

Source label: Mistral Small 3.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 78.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

160 tokens/s

#48 · Nova 2.0 Lite (medium)

AA · Jun 24, 2026

Source label: Nova 2.0 Lite (medium)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 77.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

159.4 tokens/s

#49 · Mistral Small 3

AA · Jun 24, 2026

Source label: Mistral Small 3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 77.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

157.3 tokens/s

#50 · Nova 2.0 Lite (Non-reasoning)

AA · Jun 24, 2026

Source label: Nova 2.0 Lite (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 76.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

156.6 tokens/s

#51 · Mistral Small 4

AA · Jun 24, 2026

Source label: Mistral Small 4 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

155.9 tokens/s

#52 · Llama 3.1 Instruct 8B

AA · Jun 24, 2026

Source label: Llama 3.1 Instruct 8B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 75.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

154.7 tokens/s

#53 · Ministral 3 3B

AA · Jun 24, 2026

Source label: Ministral 3 3B

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 75.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

154.1 tokens/s

#54 · Kimi K2 Thinking

AA · Jun 24, 2026

Source label: Kimi K2 Thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 74.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

151.1 tokens/s

#55 · mistral-medium-3.5

AA · Jun 24, 2026

Source label: Mistral Medium 3.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 74.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

150.6 tokens/s

#56 · Sarvam 30B (high)

AA · Jun 24, 2026

Source label: Sarvam 30B (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 73.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

150.4 tokens/s

#57 · NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

AA · Jun 24, 2026

Source label: NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 73.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

149.1 tokens/s

#58 · Mistral Small 3.2

AA · Jun 24, 2026

Source label: Mistral Small 3.2

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 72.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

143.2 tokens/s

#59 · Qwen3 30B A3B 2507 (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 30B A3B 2507 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 72.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

140.5 tokens/s

#60 · Qwen3.5 122B A10B

AA · Jun 24, 2026

Source label: Qwen3.5 122B A10B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

140.4 tokens/s

#61 · Grok 4.3

AA · Jun 24, 2026

Source label: Grok 4.3 (low)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 71.4%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

140 tokens/s

#62 · GPT-5.4 nano

AA · Jun 24, 2026

Source label: GPT-5 nano (high)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 71%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

138.1 tokens/s

#63 · Gemini 3.1 Pro Preview

AA · Jun 24, 2026

Source label: Gemini 3.1 Pro Preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 70.5%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

137.9 tokens/s

#64 · GPT-4.1

AA · Jun 24, 2026

Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 70%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

137.7 tokens/s

#65 · Gemma 4 12B (Non-reasoning)

AA · Jun 24, 2026

Source label: Gemma 4 12B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 69.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

137.4 tokens/s

#66 · Gemini 2.5 Pro

AA · Jun 24, 2026

Source label: Gemini 2.5 Pro

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 69%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

133.9 tokens/s

#67 · Nemotron 3 Ultra 550B A55B (Reasoning)

AA · Jun 24, 2026

Source label: Nemotron 3 Ultra 550B A55B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 68.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

133.6 tokens/s

#68 · Ring-2.6-1T

AA · Jun 24, 2026

Source label: Ring-2.6-1T

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 68.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

133.3 tokens/s

#69 · Nova 2.0 Pro Preview (Non-reasoning)

AA · Jun 24, 2026

Source label: Nova 2.0 Pro Preview (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 67.6%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

132.9 tokens/s

#70 · GLM-5.2 (max)

AA · Jun 24, 2026

Source label: GLM-5.2 (max)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 67.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

131.3 tokens/s

#71 · LFM2 24B A2B

AA · Jun 24, 2026

Source label: LFM2 24B A2B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 66.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

126.7 tokens/s

#72 · Gemma 4 12B (Reasoning)

AA · Jun 24, 2026

Source label: Gemma 4 12B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 66.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

126.3 tokens/s

#73 · Nova 2.0 Pro Preview (medium)

AA · Jun 24, 2026

Source label: Nova 2.0 Pro Preview (medium)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 65.7%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

125.2 tokens/s

#74 · o1

AA · Jun 24, 2026

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 65.2%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

124.1 tokens/s

#75 · minimax-m2

AA · Jun 24, 2026

Source label: MiniMax-M2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 64.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

124 tokens/s

#76 · North Mini Code

AA · Jun 24, 2026

Source label: North Mini Code

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 64.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

123.2 tokens/s

#77 · mistral-medium

AA · Jun 24, 2026

Source label: Mistral Medium

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 63.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

121.9 tokens/s

#78 · granite-4.1-8b

AA · Jun 24, 2026

Source label: Granite 4.1 8B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 63.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

121.9 tokens/s

#79 · GPT-5.4

AA · Jun 24, 2026

Source label: GPT-5.4 (low)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 62.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

121 tokens/s

#80 · glm-4.7

AA · Jun 24, 2026

Source label: GLM-4.7 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 62.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

119.6 tokens/s

#81 · Claude 4.5 Haiku (Reasoning)

AA · Jun 24, 2026

Source label: Claude 4.5 Haiku (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 61.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

119.5 tokens/s

#82 · Qwen3 VL 8B Instruct

AA · Jun 24, 2026

Source label: Qwen3 VL 8B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 61.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

118.6 tokens/s

#83 · DeepSeek V4 Flash (Non-reasoning)

AA · Jun 24, 2026

Source label: DeepSeek V4 Flash (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 61%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

116.4 tokens/s

#84 · Qwen3 VL 8B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 VL 8B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 60.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

113.1 tokens/s

#85 · Llama 4 Maverick

AA · Jun 24, 2026

Source label: Llama 4 Maverick

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 60%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

111.6 tokens/s

#86 · deepseek-v4-flash

AA · Jun 24, 2026

Source label: DeepSeek V4 Flash (Reasoning, Max Effort)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 59.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

110.2 tokens/s

#87 · Qwen3 Coder Next

AA · Jun 24, 2026

Source label: Qwen3 Coder Next

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 59%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

110.2 tokens/s

#88 · Qwen3 VL 30B A3B Instruct

AA · Jun 24, 2026

Source label: Qwen3 VL 30B A3B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 58.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

109.5 tokens/s

#89 · Qwen3 30B A3B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3 30B A3B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 58.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

106.8 tokens/s

#90 · mistral-7b-instruct

AA · Jun 24, 2026

Source label: Mistral 7B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 57.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

106.7 tokens/s

#91 · Magistral Small 1.2

AA · Jun 24, 2026

Source label: Magistral Small 1.2

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 57.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

106.5 tokens/s

#92 · Ministral 3 8B

AA · Jun 24, 2026

Source label: Ministral 3 8B

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 56.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

105.5 tokens/s

#93 · Qwen3 30B A3B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 30B A3B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 56.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

105.4 tokens/s

#94 · Qwen2.5 Turbo

AA · Jun 24, 2026

Source label: Qwen2.5 Turbo

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 55.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

105 tokens/s

#95 · Llama 4 Scout

AA · Jun 24, 2026

Source label: Llama 4 Scout

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 55.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

103.9 tokens/s

#96 · Grok 3 mini Reasoning (high)

AA · Jun 24, 2026

Source label: Grok 3 mini Reasoning (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 54.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

101.4 tokens/s

#97 · Qwen3 Coder 30B A3B Instruct

AA · Jun 24, 2026

Source label: Qwen3 Coder 30B A3B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 54.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

101 tokens/s

#98 · GPT-4o

AA · Jun 24, 2026

Source label: GPT-4o (Aug '24)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 53.8%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

101 tokens/s

#99 · Hy3-preview (Reasoning)

AA · Jun 24, 2026

Source label: Hy3-preview (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 53.3%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

100.9 tokens/s

#100 · Hy3-preview (Non-reasoning)

AA · Jun 24, 2026

Source label: Hy3-preview (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 52.9%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

100.5 tokens/s

#101 · NVIDIA Nemotron Nano 9B V2 (Reasoning)

AA · Jun 24, 2026

Source label: NVIDIA Nemotron Nano 9B V2 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 52.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

98.1 tokens/s

#102 · Claude Haiku 4.5

AA · Jun 24, 2026

Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

96.8 tokens/s

#103 · Sarvam 105B (high)

AA · Jun 24, 2026

Source label: Sarvam 105B (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 51.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

94.8 tokens/s

#104 · grok-build-0-1-06-16

AA · Jun 24, 2026

Source label: Grok Build 0.1 0616

verified runtimeexact direct

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 51%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

94.6 tokens/s

#105 · GPT-5.4 mini

AA · Jun 24, 2026

Source label: GPT-5 mini (high)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 50.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

94.6 tokens/s

#106 · glm-5.1

AA · Jun 24, 2026

Source label: GLM-5.1 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 50%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

93.9 tokens/s

#107 · Qwen3 32B

AA · Jun 24, 2026

Source label: Qwen3 32B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 49.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

93.6 tokens/s

#108 · DeepSeek V4 Pro (Non-reasoning)

AA · Jun 24, 2026

Source label: DeepSeek V4 Pro (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 49%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

93.4 tokens/s

#109 · GPT-5.1

AA · Jun 24, 2026

Source label: GPT-5.1 (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 48.6%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

92.7 tokens/s

#110 · Qwen3 Omni 30B A3B Instruct

AA · Jun 24, 2026

Source label: Qwen3 Omni 30B A3B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 48.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

92.7 tokens/s

#111 · Llama 3.3 Instruct 70B

AA · Jun 24, 2026

Source label: Llama 3.3 Instruct 70B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 47.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

91.8 tokens/s

#112 · minimax-m3

AA · Jun 24, 2026

Source label: MiniMax-M3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 47.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

90.6 tokens/s

#113 · Mistral Medium 3.1

AA · Jun 24, 2026

Source label: Mistral Medium 3.1

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 46.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

90.2 tokens/s

#114 · GPT-5.3 Codex

AA · Jun 24, 2026

Source label: GPT-5.3 Codex (xhigh)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 46.2%
Last updated: recent
Eligibility: specialized_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

87.8 tokens/s

#115 · GPT-4.1 mini

AA · Jun 24, 2026

Source label: GPT-4.1 mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 45.7%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

87.3 tokens/s

#116 · NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

AA · Jun 24, 2026

Source label: NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 45.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

87.2 tokens/s

#117 · glm-4.7-flash

AA · Jun 24, 2026

Source label: GLM-4.7-Flash (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 44.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

86.8 tokens/s

#118 · GPT-5

AA · Jun 24, 2026

Source label: GPT-5 (low)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 44.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

86.4 tokens/s

#119 · Llama 3.2 Instruct 1B

AA · Jun 24, 2026

Source label: Llama 3.2 Instruct 1B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 43.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

84.8 tokens/s

#120 · Ministral 3 14B

AA · Jun 24, 2026

Source label: Ministral 3 14B

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 43.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

84 tokens/s

#121 · Qwen3 Omni 30B A3B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 Omni 30B A3B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 42.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

82.5 tokens/s

#122 · glm-4.5-air

AA · Jun 24, 2026

Source label: GLM-4.5-Air

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 42.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

81.3 tokens/s

#123 · Qwen3.5 27B

AA · Jun 24, 2026

Source label: Qwen3.5 27B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 41.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

79.8 tokens/s

#124 · glm-4.6v

AA · Jun 24, 2026

Source label: GLM-4.6V (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 41.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

77.3 tokens/s

#125 · deepseek-v4-pro

AA · Jun 24, 2026

Source label: DeepSeek V4 Pro (Reasoning, Max Effort)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 41%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

77.1 tokens/s

#126 · MiMo-V2-Flash (Reasoning)

AA · Jun 24, 2026

Source label: MiMo-V2-Flash (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 40.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

74.4 tokens/s

#127 · mimo-v2-omni

AA · Jun 24, 2026

Source label: MiMo-V2-Omni

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 40%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

74.1 tokens/s

#128 · MiMo-V2-Omni-0327

AA · Jun 24, 2026

Source label: MiMo-V2-Omni-0327

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 39.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

72.4 tokens/s

#129 · mimo-v2-flash (non-thinking)

AA · Jun 24, 2026

Source label: MiMo-V2-Flash (Feb 2026)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 39%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

72.2 tokens/s

#130 · glm-5

AA · Jun 24, 2026

Source label: GLM-5 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 38.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

72.1 tokens/s

#131 · GPT-5.2

AA · Jun 24, 2026

Source label: GPT-5.2 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 38.1%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

70.1 tokens/s

#132 · Claude Opus 4.8

AA · Jun 24, 2026

Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 37.6%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

69.8 tokens/s

#133 · Command A+

AA · Jun 24, 2026

Source label: Command A

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 37.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

68.9 tokens/s

#134 · Qwen3 235B A22B 2507 (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 235B A22B 2507 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 36.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

68.1 tokens/s

#135 · mimo-v2.5

AA · Jun 24, 2026

Source label: MiMo-V2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 36.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

66.3 tokens/s

#136 · DeepSeek R1 Distill Llama 70B

AA · Jun 24, 2026

Source label: DeepSeek R1 Distill Llama 70B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 35.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

65.8 tokens/s

#137 · GLM-5.1 (Non-reasoning)

AA · Jun 24, 2026

Source label: GLM-5.1 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 35.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

65.3 tokens/s

#138 · Qwen3 Max

AA · Jun 24, 2026

Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 34.8%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

64.8 tokens/s

#139 · Qwen3.6 27B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3.6 27B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 34.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

64.5 tokens/s

#140 · Qwen3 VL 32B Instruct

AA · Jun 24, 2026

Source label: Qwen3 VL 32B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 33.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

63.3 tokens/s

#141 · qwen3-235b-a22b-instruct-2507

AA · Jun 24, 2026

Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 33.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

63.2 tokens/s

#142 · Qwen3.6 27B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3.6 27B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 32.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

63.1 tokens/s

#143 · Llama 3.1 Instruct 405B

AA · Jun 24, 2026

Source label: Llama 3.1 Instruct 405B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 32.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

62.6 tokens/s

#144 · Qwen3.5 9B

AA · Jun 24, 2026

Source label: Qwen3.5 9B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 31.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

61.3 tokens/s

#145 · Qwen3 14B

AA · Jun 24, 2026

Source label: Qwen3 14B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 31.4%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

61.2 tokens/s

#146 · GPT-5.5

AA · Jun 24, 2026

Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 31%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

61 tokens/s

#147 · GLM-5 (Non-reasoning)

AA · Jun 24, 2026

Source label: GLM-5 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 30.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

60.1 tokens/s

#148 · Qwen3-Coder 480B A35B

AA · Jun 24, 2026

Source label: Qwen3 Coder 480B A35B Instruct

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 30%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

59.8 tokens/s

#149 · Llama 3.2 Instruct 90B (Vision)

AA · Jun 24, 2026

Source label: Llama 3.2 Instruct 90B (Vision)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 29.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

59.3 tokens/s

#150 · Jamba 1.7 Large

AA · Jun 24, 2026

Source label: Jamba 1.7 Large

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 29%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

58 tokens/s

#151 · Jamba 1.6 Large

AA · Jun 24, 2026

Source label: Jamba 1.6 Large

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 28.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

57.9 tokens/s

#152 · Reka Flash (Sep '24)

AA · Jun 24, 2026

Source label: Reka Flash (Sep '24)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 28.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

57.7 tokens/s

#153 · Qwen3 235B A22B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3 235B A22B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 27.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

57 tokens/s

#154 · Devstral Small 2

AA · Jun 24, 2026

Source label: Devstral Small 2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 27.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

56.4 tokens/s

#155 · ling-flash-2.0

AA · Jun 24, 2026

Source label: Ling-flash-2.0

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 26.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

55.8 tokens/s

#156 · Qwen3 VL 235B A22B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 VL 235B A22B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 26.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

55.8 tokens/s

#157 · pixtral-large-2411

AA · Jun 24, 2026

Source label: Pixtral Large

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 25.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

55.7 tokens/s

#158 · GPT-4o mini

AA · Jun 24, 2026

Source label: GPT-4o mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 25.2%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

54.4 tokens/s

#159 · mimo-v2-pro

AA · Jun 24, 2026

Source label: MiMo-V2-Pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 24.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

54.3 tokens/s

#160 · glm-4.5

AA · Jun 24, 2026

Source label: GLM-4.5 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 24.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

53.6 tokens/s

#161 · Mistral Large 3

AA · Jun 24, 2026

Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 23.8%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

53.3 tokens/s

#162 · minimax-m2.7

AA · Jun 24, 2026

Source label: MiniMax-M2.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 23.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

53.2 tokens/s

#163 · Mistral Large 2 (Nov '24)

AA · Jun 24, 2026

Source label: Mistral Large 2 (Nov '24)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 22.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

53.1 tokens/s

#164 · Qwen3 Max Thinking

AA · Jun 24, 2026

Source label: Qwen3 Max Thinking (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 22.4%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

53.1 tokens/s

#165 · Claude Opus 4.5

AA · Jun 24, 2026

Source label: Claude Opus 4.5 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 21.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

52.4 tokens/s

#166 · Llama 3.2 Instruct 11B (Vision)

AA · Jun 24, 2026

Source label: Llama 3.2 Instruct 11B (Vision)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 21.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

52.2 tokens/s

#167 · qwen3.6-plus

AA · Jun 24, 2026

Source label: Qwen3.6 Plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 21%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

52.1 tokens/s

#168 · Kimi K2.7 Code

AA · Jun 24, 2026

Source label: Kimi K2.7 Code

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 20.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.9 tokens/s

#169 · Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)

AA · Jun 24, 2026

Source label: Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 20%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.7 tokens/s

#170 · Llama 3.2 Instruct 3B

AA · Jun 24, 2026

Source label: Llama 3.2 Instruct 3B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 19.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.7 tokens/s

#171 · Gemma 3n E4B Instruct

AA · Jun 24, 2026

Source label: Gemma 3n E4B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 19%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.5 tokens/s

#172 · qwen3-vl-235b-a22b-instruct

AA · Jun 24, 2026

Source label: Qwen3 VL 235B A22B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 18.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.1 tokens/s

#173 · Llama Nemotron Super 49B v1.5 (Non-reasoning)

AA · Jun 24, 2026

Source label: Llama Nemotron Super 49B v1.5 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 18.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

50.2 tokens/s

#174 · Qwen3.5 397B A17B

AA · Jun 24, 2026

Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 17.6%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

49.7 tokens/s

#175 · Qwen3.5 Omni Plus

AA · Jun 24, 2026

Source label: Qwen3.5 Omni Plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 17.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.8 tokens/s

#176 · Claude Opus 4.7

AA · Jun 24, 2026

Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 16.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.5 tokens/s

#177 · Claude Sonnet 4.6

AA · Jun 24, 2026

Source label: Claude Sonnet 4.6 (Non-reasoning, Low Effort)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 16.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.4 tokens/s

#178 · Kimi K2.5 (Reasoning)

AA · Jun 24, 2026

Source label: Kimi K2.5 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 15.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.3 tokens/s

#179 · Qwen3.7 Plus

AA · Jun 24, 2026

Source label: Qwen3.7 Plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 15.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.1 tokens/s

#180 · glm-4.6

AA · Jun 24, 2026

Source label: GLM-4.6 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 14.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48 tokens/s

#181 · Claude Sonnet 4.5

AA · Jun 24, 2026

Source label: Claude 4.5 Sonnet (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 14.3%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

47.1 tokens/s

#182 · mimo-v2.5-pro

AA · Jun 24, 2026

Source label: MiMo-V2.5-Pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 13.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.8 tokens/s

#183 · o3-pro

AA · Jun 24, 2026

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 13.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.7 tokens/s

#184 · Mistral Medium 3

AA · Jun 24, 2026

Source label: Mistral Medium 3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 12.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.7 tokens/s

#185 · Devstral 2

AA · Jun 24, 2026

Source label: Devstral 2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 12.4%
Last updated: recent
Eligibility: specialized_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.5 tokens/s

#186 · Devstral Medium

AA · Jun 24, 2026

Source label: Devstral Medium

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 11.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.3 tokens/s

#187 · Claude Opus 4.6

AA · Jun 24, 2026

Source label: Claude Opus 4.6 (Non-reasoning, High Effort)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 11.4%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

45.6 tokens/s

#188 · Qwen3.6 Max Preview

AA · Jun 24, 2026

Source label: Qwen3.6 Max Preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 11%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

44.7 tokens/s

#189 · Phi-4 Mini Instruct

AA · Jun 24, 2026

Source label: Phi-4 Mini Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 10.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

44.3 tokens/s

#190 · kimi-k2.6

AA · Jun 24, 2026

Source label: Kimi K2.6 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 10%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

42.7 tokens/s

#191 · glm-4.5v

AA · Jun 24, 2026

Source label: GLM-4.5V (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 9.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

42.7 tokens/s

#192 · Gemma 4 26B A4B

AA · Jun 24, 2026

Source label: Gemma 4 26B A4B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

41.4 tokens/s

#193 · Magistral Medium 1.2

AA · Jun 24, 2026

Source label: Magistral Medium 1.2

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 8.6%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

38.4 tokens/s

#194 · Qwen3 8B

AA · Jun 24, 2026

Source label: Qwen3 8B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 8.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

38 tokens/s

#195 · Claude Opus 4.1

AA · Jun 24, 2026

Source label: Claude 4.1 Opus (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 7.6%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.6 tokens/s

#196 · Claude Opus 4

AA · Jun 24, 2026

Source label: Claude 4.1 Opus (Non-reasoning)

backfilledproxy backfilledBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 7.6%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.
Identity: benchmark proxy (0.58)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`. Backfilled from Claude Opus 4.1 via approved benchmark identity mapping map-claude-opus-4-to-4-1.

35.6 tokens/s

#197 · Qwen3.5 4B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3.5 4B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 6.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.5 tokens/s

#198 · Devstral Small (Jul '25)

AA · Jun 24, 2026

Source label: Devstral Small (Jul '25)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 6.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.5 tokens/s

#199 · Llama 3.1 Instruct 70B

AA · Jun 24, 2026

Source label: Llama 3.1 Instruct 70B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 5.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.4 tokens/s

#200 · phi-4

AA · Jun 24, 2026

Source label: Phi-4

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 5.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.4 tokens/s

#201 · gemma-4-31b

AA · Jun 24, 2026

Source label: Gemma 4 31B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 4.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.2 tokens/s

#202 · Nova Premier

AA · Jun 24, 2026

Source label: Nova Premier

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 4.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

33.1 tokens/s

#203 · GPT-4 Turbo

AA · Jun 24, 2026

Source label: GPT-4 Turbo

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 3.8%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

33 tokens/s

#204 · Seed-OSS-36B-Instruct

AA · Jun 24, 2026

Source label: Seed-OSS-36B-Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 3.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

33 tokens/s

#205 · Qwen3.5 4B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3.5 4B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 2.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

32.5 tokens/s

#206 · Qwen3.5 0.8B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3.5 0.8B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 2.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

30.5 tokens/s

#207 · qwq-32b

AA · Jun 24, 2026

Source label: QwQ 32B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 1.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

30.1 tokens/s

#208 · Qwen3.5 2B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3.5 2B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 1.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

29.9 tokens/s

#209 · Kimi K2

AA · Jun 24, 2026

Source label: Kimi K2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

26.6 tokens/s

#210 · Kimi K2 0905

AA · Jun 24, 2026

Source label: Kimi K2 0905

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 0.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

26.2 tokens/s

#211 · Phi-4 Multimodal Instruct

AA · Jun 24, 2026

Source label: Phi-4 Multimodal Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 0%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

15.8 tokens/s

Benchmarks · /benchmarks/artificial-analysis-output-speed

Output Speed

Median output generation speed reported by Artificial Analysis.

Source · Artificial Analysis
Version · artificial-analysis snapshot 2026-06-24
Scores · 211

Test details

Visible tradeoffsThis is an efficiency signal, so it belongs beside quality rather than being mistaken for quality.

source

Artificial Analysis

metric

Tokens per second (tokens/s)

judge

Speed / cost

direction

higher better

group id

aa_output_speed_current

domain

Chat / text

What it measures vs what it misses

✓ Measures

Streaming output speed after generation begins.

✗ Misses

Answer quality and time spent reasoning before output starts.

Leaderboard · this benchmark version

#1 · mercury-2

AA · Jun 24, 2026

Source label: Mercury 2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 100%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

978.6 tokens/s

#2 · LFM2 1.2B

AA · Jun 24, 2026

Source label: LFM2 1.2B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 99.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

555.4 tokens/s

#3 · LFM2.5-1.2B-Instruct

AA · Jun 24, 2026

Source label: LFM2.5-1.2B-Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 99%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

496.6 tokens/s

#4 · Granite 4.0 H Small

AA · Jun 24, 2026

Source label: Granite 4.0 H Small

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 98.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

453.9 tokens/s

#5 · LFM2.5-VL-1.6B

AA · Jun 24, 2026

Source label: LFM2.5-VL-1.6B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 98.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

442.4 tokens/s

#6 · Step 3.7 Flash

AA · Jun 24, 2026

Source label: Step 3.7 Flash

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 97.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

421.9 tokens/s

#7 · Gemini 3.1 Flash-Lite Preview

AA · Jun 24, 2026

Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 97.1%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

367.6 tokens/s

#8 · HyperNova 60B 2605

AA · Jun 24, 2026

Source label: HyperNova 60B 2605

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 96.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

367.5 tokens/s

#9 · Granite 3.3 8B (Non-reasoning)

AA · Jun 24, 2026

Source label: Granite 3.3 8B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 96.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

361.1 tokens/s

#10 · GPT-OSS 120B

AA · Jun 24, 2026

Source label: gpt-oss-120b (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 95.7%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

336.3 tokens/s

#11 · LFM2 2.6B

AA · Jun 24, 2026

Source label: LFM2 2.6B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 95.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

333.1 tokens/s

#12 · Nova Micro

AA · Jun 24, 2026

Source label: Nova Micro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 94.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

307.9 tokens/s

#13 · Nemotron 3 Nano Omni 30B A3B Reasoning

AA · Jun 24, 2026

Source label: Nemotron 3 Nano Omni 30B A3B Reasoning

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 94.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

275 tokens/s

#14 · Qwen3.5 Omni Flash

AA · Jun 24, 2026

Source label: Qwen3.5 Omni Flash

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 93.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

273.1 tokens/s

#15 · trinity-large-thinking

AA · Jun 24, 2026

Source label: Trinity Large Thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 93.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

253.4 tokens/s

#16 · Llama 3.1 Nemotron Instruct 70B

AA · Jun 24, 2026

Source label: Llama 3.1 Nemotron Instruct 70B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 92.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

247.6 tokens/s

#17 · minimax-m2.5

AA · Jun 24, 2026

Source label: MiniMax-M2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 92.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

242.5 tokens/s

#18 · Gemini 2.5 Flash-Lite

AA · Jun 24, 2026

Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 91.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

236 tokens/s

#19 · LFM2.5-8B-A1B

AA · Jun 24, 2026

Source label: LFM2.5-8B-A1B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 91.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

230.2 tokens/s

#20 · Gemini 2.5 Flash

AA · Jun 24, 2026

Source label: Gemini 2.5 Flash (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 91%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

228.7 tokens/s

#21 · Grok 4.20

AA · Jun 24, 2026

Source label: Grok 4.20 0309 v2 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 90.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

226.5 tokens/s

#22 · MiniMax-M2.1

AA · Jun 24, 2026

Source label: MiniMax-M2.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 90%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

225.9 tokens/s

#23 · GPT-OSS 20B

AA · Jun 24, 2026

Source label: gpt-oss-20B (low)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 89.5%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

223.2 tokens/s

#24 · Grok 4.20 0309 (Non-reasoning)

AA · Jun 24, 2026

Source label: Grok 4.20 0309 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 89%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

213.2 tokens/s

#25 · NVIDIA Nemotron Nano 12B v2 VL (Reasoning)

AA · Jun 24, 2026

Source label: NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 88.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

211.2 tokens/s

#26 · nvidia-nemotron-3-super-120b-a12b

AA · Jun 24, 2026

Source label: NVIDIA Nemotron 3 Super 120B A12B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 88.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

211 tokens/s

#27 · step-3.5-flash

AA · Jun 24, 2026

Source label: Step 3.5 Flash 2603

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 87.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

207.2 tokens/s

#28 · Qwen3.7 Max

AA · Jun 24, 2026

Source label: Qwen3.7 Max

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 87.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

201.9 tokens/s

#29 · Step 3.5 Flash

AA · Jun 24, 2026

Source label: Step 3.5 Flash

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 86.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

201.1 tokens/s

#30 · o3 mini

AA · Jun 24, 2026

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 86.2%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

197.8 tokens/s

#31 · Qwen3.6 35B A3B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3.6 35B A3B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 85.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

187.2 tokens/s

#32 · Gemini 3 Flash

AA · Jun 24, 2026

Source label: Gemini 3 Flash Preview (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 85.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

186.8 tokens/s

#33 · qwen3-next-80b-a3b-instruct

AA · Jun 24, 2026

Source label: Qwen3 Next 80B A3B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 84.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

183.6 tokens/s

#34 · Jamba 1.6 Mini

AA · Jun 24, 2026

Source label: Jamba 1.6 Mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 84.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

180 tokens/s

#35 · GPT-4.1 nano

AA · Jun 24, 2026

Source label: GPT-4.1 nano

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 83.8%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

179.6 tokens/s

#36 · Gemini 3.5 Flash

AA · Jun 24, 2026

Source label: Gemini 3.5 Flash (minimal)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

177.8 tokens/s

#37 · Mistral Small (Sep '24)

AA · Jun 24, 2026

Source label: Mistral Small (Sep '24)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 82.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

176.2 tokens/s

#38 · Qwen3.6 35B A3B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3.6 35B A3B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 82.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

175.9 tokens/s

#39 · Nova 2.0 Lite (low)

AA · Jun 24, 2026

Source label: Nova 2.0 Lite (low)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 81.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

172.7 tokens/s

#40 · Nova Lite

AA · Jun 24, 2026

Source label: Nova Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 81.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

172.2 tokens/s

#41 · o4 mini

AA · Jun 24, 2026

Source label: o4-mini (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 81%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

170.9 tokens/s

#42 · Qwen3 30B A3B 2507 Instruct

AA · Jun 24, 2026

Source label: Qwen3 30B A3B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 80.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

166.4 tokens/s

#43 · Mistral Small (Feb '24)

AA · Jun 24, 2026

Source label: Mistral Small (Feb '24)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 80%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

163.3 tokens/s

#44 · o3

AA · Jun 24, 2026

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 79.5%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

162.6 tokens/s

#45 · Nova 2.0 Lite (high)

AA · Jun 24, 2026

Source label: Nova 2.0 Lite (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 79%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

162.6 tokens/s

#46 · Qwen3.5 35B A3B

AA · Jun 24, 2026

Source label: Qwen3.5 35B A3B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 78.6%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

161.6 tokens/s

#47 · Mistral Small 3.1

AA · Jun 24, 2026

Source label: Mistral Small 3.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 78.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

160 tokens/s

#48 · Nova 2.0 Lite (medium)

AA · Jun 24, 2026

Source label: Nova 2.0 Lite (medium)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 77.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

159.4 tokens/s

#49 · Mistral Small 3

AA · Jun 24, 2026

Source label: Mistral Small 3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 77.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

157.3 tokens/s

#50 · Nova 2.0 Lite (Non-reasoning)

AA · Jun 24, 2026

Source label: Nova 2.0 Lite (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 76.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

156.6 tokens/s

#51 · Mistral Small 4

AA · Jun 24, 2026

Source label: Mistral Small 4 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

155.9 tokens/s

#52 · Llama 3.1 Instruct 8B

AA · Jun 24, 2026

Source label: Llama 3.1 Instruct 8B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 75.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

154.7 tokens/s

#53 · Ministral 3 3B

AA · Jun 24, 2026

Source label: Ministral 3 3B

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 75.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

154.1 tokens/s

#54 · Kimi K2 Thinking

AA · Jun 24, 2026

Source label: Kimi K2 Thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 74.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

151.1 tokens/s

#55 · mistral-medium-3.5

AA · Jun 24, 2026

Source label: Mistral Medium 3.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 74.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

150.6 tokens/s

#56 · Sarvam 30B (high)

AA · Jun 24, 2026

Source label: Sarvam 30B (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 73.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

150.4 tokens/s

#57 · NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

AA · Jun 24, 2026

Source label: NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 73.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

149.1 tokens/s

#58 · Mistral Small 3.2

AA · Jun 24, 2026

Source label: Mistral Small 3.2

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 72.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

143.2 tokens/s

#59 · Qwen3 30B A3B 2507 (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 30B A3B 2507 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 72.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

140.5 tokens/s

#60 · Qwen3.5 122B A10B

AA · Jun 24, 2026

Source label: Qwen3.5 122B A10B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 71.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

140.4 tokens/s

#61 · Grok 4.3

AA · Jun 24, 2026

Source label: Grok 4.3 (low)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 71.4%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

140 tokens/s

#62 · GPT-5.4 nano

AA · Jun 24, 2026

Source label: GPT-5 nano (high)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 71%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

138.1 tokens/s

#63 · Gemini 3.1 Pro Preview

AA · Jun 24, 2026

Source label: Gemini 3.1 Pro Preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 70.5%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

137.9 tokens/s

#64 · GPT-4.1

AA · Jun 24, 2026

Source label: GPT-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 70%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

137.7 tokens/s

#65 · Gemma 4 12B (Non-reasoning)

AA · Jun 24, 2026

Source label: Gemma 4 12B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 69.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

137.4 tokens/s

#66 · Gemini 2.5 Pro

AA · Jun 24, 2026

Source label: Gemini 2.5 Pro

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 69%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

133.9 tokens/s

#67 · Nemotron 3 Ultra 550B A55B (Reasoning)

AA · Jun 24, 2026

Source label: Nemotron 3 Ultra 550B A55B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 68.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

133.6 tokens/s

#68 · Ring-2.6-1T

AA · Jun 24, 2026

Source label: Ring-2.6-1T

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 68.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

133.3 tokens/s

#69 · Nova 2.0 Pro Preview (Non-reasoning)

AA · Jun 24, 2026

Source label: Nova 2.0 Pro Preview (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 67.6%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

132.9 tokens/s

#70 · GLM-5.2 (max)

AA · Jun 24, 2026

Source label: GLM-5.2 (max)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 67.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

131.3 tokens/s

#71 · LFM2 24B A2B

AA · Jun 24, 2026

Source label: LFM2 24B A2B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 66.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

126.7 tokens/s

#72 · Gemma 4 12B (Reasoning)

AA · Jun 24, 2026

Source label: Gemma 4 12B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 66.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

126.3 tokens/s

#73 · Nova 2.0 Pro Preview (medium)

AA · Jun 24, 2026

Source label: Nova 2.0 Pro Preview (medium)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 65.7%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

125.2 tokens/s

#74 · o1

AA · Jun 24, 2026

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 65.2%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

124.1 tokens/s

#75 · minimax-m2

AA · Jun 24, 2026

Source label: MiniMax-M2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 64.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

124 tokens/s

#76 · North Mini Code

AA · Jun 24, 2026

Source label: North Mini Code

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 64.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

123.2 tokens/s

#77 · mistral-medium

AA · Jun 24, 2026

Source label: Mistral Medium

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 63.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

121.9 tokens/s

#78 · granite-4.1-8b

AA · Jun 24, 2026

Source label: Granite 4.1 8B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 63.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

121.9 tokens/s

#79 · GPT-5.4

AA · Jun 24, 2026

Source label: GPT-5.4 (low)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 62.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

121 tokens/s

#80 · glm-4.7

AA · Jun 24, 2026

Source label: GLM-4.7 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 62.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

119.6 tokens/s

#81 · Claude 4.5 Haiku (Reasoning)

AA · Jun 24, 2026

Source label: Claude 4.5 Haiku (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 61.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

119.5 tokens/s

#82 · Qwen3 VL 8B Instruct

AA · Jun 24, 2026

Source label: Qwen3 VL 8B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 61.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

118.6 tokens/s

#83 · DeepSeek V4 Flash (Non-reasoning)

AA · Jun 24, 2026

Source label: DeepSeek V4 Flash (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 61%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

116.4 tokens/s

#84 · Qwen3 VL 8B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 VL 8B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 60.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

113.1 tokens/s

#85 · Llama 4 Maverick

AA · Jun 24, 2026

Source label: Llama 4 Maverick

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 60%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

111.6 tokens/s

#86 · deepseek-v4-flash

AA · Jun 24, 2026

Source label: DeepSeek V4 Flash (Reasoning, Max Effort)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 59.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

110.2 tokens/s

#87 · Qwen3 Coder Next

AA · Jun 24, 2026

Source label: Qwen3 Coder Next

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 59%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

110.2 tokens/s

#88 · Qwen3 VL 30B A3B Instruct

AA · Jun 24, 2026

Source label: Qwen3 VL 30B A3B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 58.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

109.5 tokens/s

#89 · Qwen3 30B A3B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3 30B A3B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 58.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

106.8 tokens/s

#90 · mistral-7b-instruct

AA · Jun 24, 2026

Source label: Mistral 7B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 57.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

106.7 tokens/s

#91 · Magistral Small 1.2

AA · Jun 24, 2026

Source label: Magistral Small 1.2

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 57.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

106.5 tokens/s

#92 · Ministral 3 8B

AA · Jun 24, 2026

Source label: Ministral 3 8B

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 56.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

105.5 tokens/s

#93 · Qwen3 30B A3B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 30B A3B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 56.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

105.4 tokens/s

#94 · Qwen2.5 Turbo

AA · Jun 24, 2026

Source label: Qwen2.5 Turbo

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 55.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

105 tokens/s

#95 · Llama 4 Scout

AA · Jun 24, 2026

Source label: Llama 4 Scout

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 55.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

103.9 tokens/s

#96 · Grok 3 mini Reasoning (high)

AA · Jun 24, 2026

Source label: Grok 3 mini Reasoning (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 54.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

101.4 tokens/s

#97 · Qwen3 Coder 30B A3B Instruct

AA · Jun 24, 2026

Source label: Qwen3 Coder 30B A3B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 54.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

101 tokens/s

#98 · GPT-4o

AA · Jun 24, 2026

Source label: GPT-4o (Aug '24)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 53.8%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

101 tokens/s

#99 · Hy3-preview (Reasoning)

AA · Jun 24, 2026

Source label: Hy3-preview (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 53.3%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

100.9 tokens/s

#100 · Hy3-preview (Non-reasoning)

AA · Jun 24, 2026

Source label: Hy3-preview (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 52.9%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

100.5 tokens/s

#101 · NVIDIA Nemotron Nano 9B V2 (Reasoning)

AA · Jun 24, 2026

Source label: NVIDIA Nemotron Nano 9B V2 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 52.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

98.1 tokens/s

#102 · Claude Haiku 4.5

AA · Jun 24, 2026

Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

96.8 tokens/s

#103 · Sarvam 105B (high)

AA · Jun 24, 2026

Source label: Sarvam 105B (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 51.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

94.8 tokens/s

#104 · grok-build-0-1-06-16

AA · Jun 24, 2026

Source label: Grok Build 0.1 0616

verified runtimeexact direct

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 51%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

94.6 tokens/s

#105 · GPT-5.4 mini

AA · Jun 24, 2026

Source label: GPT-5 mini (high)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 50.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

94.6 tokens/s

#106 · glm-5.1

AA · Jun 24, 2026

Source label: GLM-5.1 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 50%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

93.9 tokens/s

#107 · Qwen3 32B

AA · Jun 24, 2026

Source label: Qwen3 32B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 49.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

93.6 tokens/s

#108 · DeepSeek V4 Pro (Non-reasoning)

AA · Jun 24, 2026

Source label: DeepSeek V4 Pro (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 49%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

93.4 tokens/s

#109 · GPT-5.1

AA · Jun 24, 2026

Source label: GPT-5.1 (high)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 48.6%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

92.7 tokens/s

#110 · Qwen3 Omni 30B A3B Instruct

AA · Jun 24, 2026

Source label: Qwen3 Omni 30B A3B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 48.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

92.7 tokens/s

#111 · Llama 3.3 Instruct 70B

AA · Jun 24, 2026

Source label: Llama 3.3 Instruct 70B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 47.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

91.8 tokens/s

#112 · minimax-m3

AA · Jun 24, 2026

Source label: MiniMax-M3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 47.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

90.6 tokens/s

#113 · Mistral Medium 3.1

AA · Jun 24, 2026

Source label: Mistral Medium 3.1

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 46.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

90.2 tokens/s

#114 · GPT-5.3 Codex

AA · Jun 24, 2026

Source label: GPT-5.3 Codex (xhigh)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 46.2%
Last updated: recent
Eligibility: specialized_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

87.8 tokens/s

#115 · GPT-4.1 mini

AA · Jun 24, 2026

Source label: GPT-4.1 mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 45.7%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

87.3 tokens/s

#116 · NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

AA · Jun 24, 2026

Source label: NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 45.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

87.2 tokens/s

#117 · glm-4.7-flash

AA · Jun 24, 2026

Source label: GLM-4.7-Flash (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 44.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

86.8 tokens/s

#118 · GPT-5

AA · Jun 24, 2026

Source label: GPT-5 (low)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 44.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

86.4 tokens/s

#119 · Llama 3.2 Instruct 1B

AA · Jun 24, 2026

Source label: Llama 3.2 Instruct 1B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 43.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

84.8 tokens/s

#120 · Ministral 3 14B

AA · Jun 24, 2026

Source label: Ministral 3 14B

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 43.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

84 tokens/s

#121 · Qwen3 Omni 30B A3B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 Omni 30B A3B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 42.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

82.5 tokens/s

#122 · glm-4.5-air

AA · Jun 24, 2026

Source label: GLM-4.5-Air

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 42.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

81.3 tokens/s

#123 · Qwen3.5 27B

AA · Jun 24, 2026

Source label: Qwen3.5 27B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 41.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

79.8 tokens/s

#124 · glm-4.6v

AA · Jun 24, 2026

Source label: GLM-4.6V (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 41.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

77.3 tokens/s

#125 · deepseek-v4-pro

AA · Jun 24, 2026

Source label: DeepSeek V4 Pro (Reasoning, Max Effort)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 41%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

77.1 tokens/s

#126 · MiMo-V2-Flash (Reasoning)

AA · Jun 24, 2026

Source label: MiMo-V2-Flash (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 40.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

74.4 tokens/s

#127 · mimo-v2-omni

AA · Jun 24, 2026

Source label: MiMo-V2-Omni

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 40%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

74.1 tokens/s

#128 · MiMo-V2-Omni-0327

AA · Jun 24, 2026

Source label: MiMo-V2-Omni-0327

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 39.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

72.4 tokens/s

#129 · mimo-v2-flash (non-thinking)

AA · Jun 24, 2026

Source label: MiMo-V2-Flash (Feb 2026)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 39%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

72.2 tokens/s

#130 · glm-5

AA · Jun 24, 2026

Source label: GLM-5 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 38.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

72.1 tokens/s

#131 · GPT-5.2

AA · Jun 24, 2026

Source label: GPT-5.2 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 38.1%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

70.1 tokens/s

#132 · Claude Opus 4.8

AA · Jun 24, 2026

Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 37.6%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

69.8 tokens/s

#133 · Command A+

AA · Jun 24, 2026

Source label: Command A

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 37.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

68.9 tokens/s

#134 · Qwen3 235B A22B 2507 (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 235B A22B 2507 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 36.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

68.1 tokens/s

#135 · mimo-v2.5

AA · Jun 24, 2026

Source label: MiMo-V2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 36.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

66.3 tokens/s

#136 · DeepSeek R1 Distill Llama 70B

AA · Jun 24, 2026

Source label: DeepSeek R1 Distill Llama 70B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 35.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

65.8 tokens/s

#137 · GLM-5.1 (Non-reasoning)

AA · Jun 24, 2026

Source label: GLM-5.1 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 35.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

65.3 tokens/s

#138 · Qwen3 Max

AA · Jun 24, 2026

Source label: Qwen3 Max (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 34.8%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

64.8 tokens/s

#139 · Qwen3.6 27B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3.6 27B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 34.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

64.5 tokens/s

#140 · Qwen3 VL 32B Instruct

AA · Jun 24, 2026

Source label: Qwen3 VL 32B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 33.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

63.3 tokens/s

#141 · qwen3-235b-a22b-instruct-2507

AA · Jun 24, 2026

Source label: Qwen3 235B A22B 2507 Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 33.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

63.2 tokens/s

#142 · Qwen3.6 27B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3.6 27B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 32.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

63.1 tokens/s

#143 · Llama 3.1 Instruct 405B

AA · Jun 24, 2026

Source label: Llama 3.1 Instruct 405B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 32.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

62.6 tokens/s

#144 · Qwen3.5 9B

AA · Jun 24, 2026

Source label: Qwen3.5 9B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 31.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

61.3 tokens/s

#145 · Qwen3 14B

AA · Jun 24, 2026

Source label: Qwen3 14B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 31.4%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

61.2 tokens/s

#146 · GPT-5.5

AA · Jun 24, 2026

Source label: GPT-5.5 (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 31%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

61 tokens/s

#147 · GLM-5 (Non-reasoning)

AA · Jun 24, 2026

Source label: GLM-5 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 30.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

60.1 tokens/s

#148 · Qwen3-Coder 480B A35B

AA · Jun 24, 2026

Source label: Qwen3 Coder 480B A35B Instruct

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 30%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

59.8 tokens/s

#149 · Llama 3.2 Instruct 90B (Vision)

AA · Jun 24, 2026

Source label: Llama 3.2 Instruct 90B (Vision)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 29.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

59.3 tokens/s

#150 · Jamba 1.7 Large

AA · Jun 24, 2026

Source label: Jamba 1.7 Large

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 29%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

58 tokens/s

#151 · Jamba 1.6 Large

AA · Jun 24, 2026

Source label: Jamba 1.6 Large

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 28.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

57.9 tokens/s

#152 · Reka Flash (Sep '24)

AA · Jun 24, 2026

Source label: Reka Flash (Sep '24)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 28.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

57.7 tokens/s

#153 · Qwen3 235B A22B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3 235B A22B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 27.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

57 tokens/s

#154 · Devstral Small 2

AA · Jun 24, 2026

Source label: Devstral Small 2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 27.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

56.4 tokens/s

#155 · ling-flash-2.0

AA · Jun 24, 2026

Source label: Ling-flash-2.0

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 26.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

55.8 tokens/s

#156 · Qwen3 VL 235B A22B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3 VL 235B A22B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 26.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

55.8 tokens/s

#157 · pixtral-large-2411

AA · Jun 24, 2026

Source label: Pixtral Large

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 25.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

55.7 tokens/s

#158 · GPT-4o mini

AA · Jun 24, 2026

Source label: GPT-4o mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 25.2%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

54.4 tokens/s

#159 · mimo-v2-pro

AA · Jun 24, 2026

Source label: MiMo-V2-Pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 24.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

54.3 tokens/s

#160 · glm-4.5

AA · Jun 24, 2026

Source label: GLM-4.5 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 24.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

53.6 tokens/s

#161 · Mistral Large 3

AA · Jun 24, 2026

Source label: Mistral Large 3

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 23.8%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

53.3 tokens/s

#162 · minimax-m2.7

AA · Jun 24, 2026

Source label: MiniMax-M2.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 23.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

53.2 tokens/s

#163 · Mistral Large 2 (Nov '24)

AA · Jun 24, 2026

Source label: Mistral Large 2 (Nov '24)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 22.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

53.1 tokens/s

#164 · Qwen3 Max Thinking

AA · Jun 24, 2026

Source label: Qwen3 Max Thinking (Preview)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 22.4%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

53.1 tokens/s

#165 · Claude Opus 4.5

AA · Jun 24, 2026

Source label: Claude Opus 4.5 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 21.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

52.4 tokens/s

#166 · Llama 3.2 Instruct 11B (Vision)

AA · Jun 24, 2026

Source label: Llama 3.2 Instruct 11B (Vision)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 21.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

52.2 tokens/s

#167 · qwen3.6-plus

AA · Jun 24, 2026

Source label: Qwen3.6 Plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 21%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

52.1 tokens/s

#168 · Kimi K2.7 Code

AA · Jun 24, 2026

Source label: Kimi K2.7 Code

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 20.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.9 tokens/s

#169 · Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)

AA · Jun 24, 2026

Source label: Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 20%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.7 tokens/s

#170 · Llama 3.2 Instruct 3B

AA · Jun 24, 2026

Source label: Llama 3.2 Instruct 3B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 19.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.7 tokens/s

#171 · Gemma 3n E4B Instruct

AA · Jun 24, 2026

Source label: Gemma 3n E4B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 19%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.5 tokens/s

#172 · qwen3-vl-235b-a22b-instruct

AA · Jun 24, 2026

Source label: Qwen3 VL 235B A22B Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 18.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.1 tokens/s

#173 · Llama Nemotron Super 49B v1.5 (Non-reasoning)

AA · Jun 24, 2026

Source label: Llama Nemotron Super 49B v1.5 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 18.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

50.2 tokens/s

#174 · Qwen3.5 397B A17B

AA · Jun 24, 2026

Source label: Qwen3.5 397B A17B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 17.6%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

49.7 tokens/s

#175 · Qwen3.5 Omni Plus

AA · Jun 24, 2026

Source label: Qwen3.5 Omni Plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 17.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.8 tokens/s

#176 · Claude Opus 4.7

AA · Jun 24, 2026

Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 16.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.5 tokens/s

#177 · Claude Sonnet 4.6

AA · Jun 24, 2026

Source label: Claude Sonnet 4.6 (Non-reasoning, Low Effort)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 16.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.4 tokens/s

#178 · Kimi K2.5 (Reasoning)

AA · Jun 24, 2026

Source label: Kimi K2.5 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 15.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.3 tokens/s

#179 · Qwen3.7 Plus

AA · Jun 24, 2026

Source label: Qwen3.7 Plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 15.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48.1 tokens/s

#180 · glm-4.6

AA · Jun 24, 2026

Source label: GLM-4.6 (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 14.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

48 tokens/s

#181 · Claude Sonnet 4.5

AA · Jun 24, 2026

Source label: Claude 4.5 Sonnet (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 14.3%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

47.1 tokens/s

#182 · mimo-v2.5-pro

AA · Jun 24, 2026

Source label: MiMo-V2.5-Pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 13.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.8 tokens/s

#183 · o3-pro

AA · Jun 24, 2026

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 13.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.7 tokens/s

#184 · Mistral Medium 3

AA · Jun 24, 2026

Source label: Mistral Medium 3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 12.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.7 tokens/s

#185 · Devstral 2

AA · Jun 24, 2026

Source label: Devstral 2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 12.4%
Last updated: recent
Eligibility: specialized_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.5 tokens/s

#186 · Devstral Medium

AA · Jun 24, 2026

Source label: Devstral Medium

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 11.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

46.3 tokens/s

#187 · Claude Opus 4.6

AA · Jun 24, 2026

Source label: Claude Opus 4.6 (Non-reasoning, High Effort)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 11.4%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

45.6 tokens/s

#188 · Qwen3.6 Max Preview

AA · Jun 24, 2026

Source label: Qwen3.6 Max Preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 11%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

44.7 tokens/s

#189 · Phi-4 Mini Instruct

AA · Jun 24, 2026

Source label: Phi-4 Mini Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 10.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

44.3 tokens/s

#190 · kimi-k2.6

AA · Jun 24, 2026

Source label: Kimi K2.6 (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 10%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

42.7 tokens/s

#191 · glm-4.5v

AA · Jun 24, 2026

Source label: GLM-4.5V (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 9.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

42.7 tokens/s

#192 · Gemma 4 26B A4B

AA · Jun 24, 2026

Source label: Gemma 4 26B A4B (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

41.4 tokens/s

#193 · Magistral Medium 1.2

AA · Jun 24, 2026

Source label: Magistral Medium 1.2

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 8.6%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

38.4 tokens/s

#194 · Qwen3 8B

AA · Jun 24, 2026

Source label: Qwen3 8B (Reasoning)

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 8.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

38 tokens/s

#195 · Claude Opus 4.1

AA · Jun 24, 2026

Source label: Claude 4.1 Opus (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 7.6%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.6 tokens/s

#196 · Claude Opus 4

AA · Jun 24, 2026

Source label: Claude 4.1 Opus (Non-reasoning)

backfilledproxy backfilledBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 7.6%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.
Identity: benchmark proxy (0.58)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`. Backfilled from Claude Opus 4.1 via approved benchmark identity mapping map-claude-opus-4-to-4-1.

35.6 tokens/s

#197 · Qwen3.5 4B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3.5 4B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 6.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.5 tokens/s

#198 · Devstral Small (Jul '25)

AA · Jun 24, 2026

Source label: Devstral Small (Jul '25)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 6.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.5 tokens/s

#199 · Llama 3.1 Instruct 70B

AA · Jun 24, 2026

Source label: Llama 3.1 Instruct 70B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 5.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.4 tokens/s

#200 · phi-4

AA · Jun 24, 2026

Source label: Phi-4

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 5.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.4 tokens/s

#201 · gemma-4-31b

AA · Jun 24, 2026

Source label: Gemma 4 31B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 4.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

35.2 tokens/s

#202 · Nova Premier

AA · Jun 24, 2026

Source label: Nova Premier

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 4.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

33.1 tokens/s

#203 · GPT-4 Turbo

AA · Jun 24, 2026

Source label: GPT-4 Turbo

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 3.8%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

33 tokens/s

#204 · Seed-OSS-36B-Instruct

AA · Jun 24, 2026

Source label: Seed-OSS-36B-Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 3.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

33 tokens/s

#205 · Qwen3.5 4B (Reasoning)

AA · Jun 24, 2026

Source label: Qwen3.5 4B (Reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 2.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

32.5 tokens/s

#206 · Qwen3.5 0.8B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3.5 0.8B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 2.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

30.5 tokens/s

#207 · qwq-32b

AA · Jun 24, 2026

Source label: QwQ 32B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 1.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

30.1 tokens/s

#208 · Qwen3.5 2B (Non-reasoning)

AA · Jun 24, 2026

Source label: Qwen3.5 2B (Non-reasoning)

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 1.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

29.9 tokens/s

#209 · Kimi K2

AA · Jun 24, 2026

Source label: Kimi K2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

26.6 tokens/s

#210 · Kimi K2 0905

AA · Jun 24, 2026

Source label: Kimi K2 0905

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 0.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

26.2 tokens/s

#211 · Phi-4 Multimodal Instruct

AA · Jun 24, 2026

Source label: Phi-4 Multimodal Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://artificialanalysis.ai/leaderboards/models
Percentile: 0%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.94)

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

15.8 tokens/s

Output Speed

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version

Loading benchmark evidence.

Output Speed

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version