Intelligence Index
AA · Chat / text · Combined
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #213 · Source label: Qwen3.5 35B A3B (Non-reasoning)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 15
- Percentile
- 61.9%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.
61.9% percentile inside its fair comparison set15Raw benchmark value
AA-Omniscience accuracy
AA · Chat / text · Objective
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #310 · Source label: Qwen3.5 35B A3B (Non-reasoning)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 15.7%
- Percentile
- 32.1%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.
32.1% percentile inside its fair comparison set15.7%Raw benchmark value
AA-Omniscience non-hallucination
AA · Chat / text · Objective
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #403 · Source label: Qwen3.5 35B A3B (Non-reasoning)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 6.6%
- Percentile
- 11.6%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.
11.6% percentile inside its fair comparison set6.6%Raw benchmark value
IFBench
AA · Chat / text · Objective
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #144 · Source label: Qwen3.5 35B A3B (Non-reasoning)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 44.5%
- Percentile
- 59%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `ifbench`.
59% percentile inside its fair comparison set44.5%Raw benchmark value
Input price
AA · Chat / text · Speed / cost
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #119 · Source label: Qwen3.5 35B A3B (Non-reasoning)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- $0.3 /1M input tokens
- Percentile
- 67.8%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.
67.8% percentile inside its fair comparison set$0.3 /1M input tokensRaw benchmark value
Output price
AA · Chat / text · Speed / cost
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #166 · Source label: Qwen3.5 35B A3B (Non-reasoning)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- $2 /1M output tokens
- Percentile
- 54.1%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.
54.1% percentile inside its fair comparison set$2 /1M output tokensRaw benchmark value
Output Speed
AA · Chat / text · Speed / cost
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #56 · Source label: Qwen3.5 35B A3B (Reasoning)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 148.8 tokens/s
- Percentile
- 79.4%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.
79.4% percentile inside its fair comparison set148.8 tokens/sRaw benchmark value
Time to first token
AA · Chat / text · Speed / cost
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #100 · Source label: Qwen3.5 35B A3B (Reasoning)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 2.11s
- Percentile
- 63.2%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.
63.2% percentile inside its fair comparison set2.11sRaw benchmark value
Time to first answer token
AA · Chat / text · Speed / cost
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #114 · Source label: Qwen3.5 35B A3B (Reasoning)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 15.55s
- Percentile
- 57.7%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.
57.7% percentile inside its fair comparison set15.55sRaw benchmark value
Text Arena
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #151 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,394
- Percentile
- 60.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: overall. Source rank: #168. Votes: 30408. Organization: alibaba. License: Apache 2.0.
60.1% percentile inside its fair comparison set1,394Raw benchmark valueCI 1,390 - 1,398
Text Arena · Creative Writing
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #166 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,342
- Percentile
- 55.9%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: creative_writing. Source rank: #186. Votes: 4672. Organization: alibaba. License: Apache 2.0.
55.9% percentile inside its fair comparison set1,342Raw benchmark valueCI 1,333 - 1,351
Text Arena · English
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #148 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,410
- Percentile
- 60.9%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: english. Source rank: #165. Votes: 13530. Organization: alibaba. License: Apache 2.0.
60.9% percentile inside its fair comparison set1,410Raw benchmark valueCI 1,404 - 1,416
Text Arena · Exclude Ties
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #149 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,373
- Percentile
- 60.6%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: exclude_ties. Source rank: #166. Votes: 22182. Organization: alibaba. License: Apache 2.0.
60.6% percentile inside its fair comparison set1,373Raw benchmark valueCI 1,368 - 1,379
Text Arena · Hard Prompts
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #155 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,412
- Percentile
- 59%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts. Source rank: #174. Votes: 19317. Organization: alibaba. License: Apache 2.0.
59% percentile inside its fair comparison set1,412Raw benchmark valueCI 1,407 - 1,417
Text Arena · Hard Prompts English
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #147 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,425
- Percentile
- 61%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts_english. Source rank: #163. Votes: 8830. Organization: alibaba. License: Apache 2.0.
61% percentile inside its fair comparison set1,425Raw benchmark valueCI 1,418 - 1,432
Text Arena · Instruction Following
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #144 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,386
- Percentile
- 62%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: instruction_following. Source rank: #162. Votes: 9915. Organization: alibaba. License: Apache 2.0.
62% percentile inside its fair comparison set1,386Raw benchmark valueCI 1,379 - 1,392
Text Arena · Longer Query
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #151 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,399
- Percentile
- 57.7%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: longer_query. Source rank: #171. Votes: 11897. Organization: alibaba. License: Apache 2.0.
57.7% percentile inside its fair comparison set1,399Raw benchmark valueCI 1,392 - 1,405
Text Arena · Multi Turn
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #150 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,395
- Percentile
- 60.2%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: multi_turn. Source rank: #169. Votes: 5482. Organization: alibaba. License: Apache 2.0.
60.2% percentile inside its fair comparison set1,395Raw benchmark valueCI 1,386 - 1,403
Text Arena · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #143 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,394
- Percentile
- 62.2%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: overall. Source rank: #159. Votes: 30408. Organization: alibaba. License: Apache 2.0.
62.2% percentile inside its fair comparison set1,394Raw benchmark valueCI 1,390 - 1,399
Text Arena · Creative Writing · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #149 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,347
- Percentile
- 60.4%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: creative_writing. Source rank: #168. Votes: 4672. Organization: alibaba. License: Apache 2.0.
60.4% percentile inside its fair comparison set1,347Raw benchmark valueCI 1,338 - 1,356
Text Arena · English · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #140 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,407
- Percentile
- 63%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: english. Source rank: #154. Votes: 13530. Organization: alibaba. License: Apache 2.0.
63% percentile inside its fair comparison set1,407Raw benchmark valueCI 1,401 - 1,413
Text Arena · Exclude Ties · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #143 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,373
- Percentile
- 62.2%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: exclude_ties. Source rank: #158. Votes: 22182. Organization: alibaba. License: Apache 2.0.
62.2% percentile inside its fair comparison set1,373Raw benchmark valueCI 1,367 - 1,379
Text Arena · Hard Prompts · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #143 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,400
- Percentile
- 62.2%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts. Source rank: #159. Votes: 19317. Organization: alibaba. License: Apache 2.0.
62.2% percentile inside its fair comparison set1,400Raw benchmark valueCI 1,394 - 1,405
Text Arena · Hard Prompts English · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #139 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,410
- Percentile
- 63.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: hard_prompts_english. Source rank: #154. Votes: 8830. Organization: alibaba. License: Apache 2.0.
63.1% percentile inside its fair comparison set1,410Raw benchmark valueCI 1,403 - 1,417
Text Arena · Instruction Following · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #139 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,379
- Percentile
- 63.3%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: instruction_following. Source rank: #154. Votes: 9915. Organization: alibaba. License: Apache 2.0.
63.3% percentile inside its fair comparison set1,379Raw benchmark valueCI 1,372 - 1,385
Text Arena · Longer Query · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #145 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,389
- Percentile
- 59.4%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: longer_query. Source rank: #162. Votes: 11897. Organization: alibaba. License: Apache 2.0.
59.4% percentile inside its fair comparison set1,389Raw benchmark valueCI 1,383 - 1,395
Text Arena · Multi Turn · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #145 · Source label: qwen3.5-35b-a3b
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,390
- Percentile
- 61.5%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `qwen3.5-35b-a3b`. Category: multi_turn. Source rank: #161. Votes: 5482. Organization: alibaba. License: Apache 2.0.
61.5% percentile inside its fair comparison set1,390Raw benchmark valueCI 1,382 - 1,399