Benchmarks · /benchmarks/vals-ai-terminal-bench-2-1

Terminal-Bench 2.1

Name: Terminal-Bench 2.1
Creator: Vals AI

Terminal-Bench 2.1 result as reported by Vals AI.

Source · Vals AI
Version · vals-ai snapshot 2026-06-24
Scores · 28

Test details

Verified but agingThis is an objective signal, so it is mainly about measurable task performance rather than public taste.

source

Vals AI

metric

Accuracy (%)

judge

Objective

direction

higher better

group id

vals_terminal_bench_2_1_current

domain

Coding

What it measures vs what it misses

✓ Measures

Difficult terminal-based agent tasks.

✗ Misses

Adjacent skills outside the benchmark task mix, latency, and cost.

Why this countsIt tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.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 fully capture repo-scale iteration, IDE ergonomics, or long debugging loops.

Leaderboard · this benchmark version

#1 · Claude Fable 5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 100%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

80.5%77.9% - 83.2%

#2 · GPT-5.5

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 96.3%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: OpenAI.

76.4%75.1% - 77.7%

#3 · Gemini 3.5 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 92.6%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

74.2%72% - 76.4%

#4 · Claude Opus 4.8

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 88.9%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

71.9%70.6% - 73.2%

#5 · Gemini 3.1 Pro Preview

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.1-pro-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 85.2%
Last updated: aging
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

70.8%68.6% - 73%

#6 · Claude Opus 4.7

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 81.5%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

68.5%66% - 71.1%

#7 · glm-5.2-max

VALS-AI · Jun 17, 2026

Source label: zai/glm-5.2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 77.8%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Zhipu AI.

67.8%65.8% - 69.7%

#8 · kimi-k2.7-code

VALS-AI · Jun 17, 2026

Source label: kimi/kimi-k2.7-code

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 74.1%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Moonshot AI.

67%66.3% - 67.8%

#9 · Qwen3.7 Max

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.7-max

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 70.4%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Alibaba.

61%60.3% - 61.8%

#10 · mimo-v2.5

VALS-AI · Jun 17, 2026

Source label: xiaomi/mimo-v2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 66.7%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Xiaomi.

60.7%50.5% - 70.9%

#11 · Claude Sonnet 4.6

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-sonnet-4-6

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 63%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

57.3%56% - 58.6%

#12 · mimo-v2.5-pro

VALS-AI · Jun 17, 2026

Source label: xiaomi/mimo-v2.5-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 63%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Xiaomi.

57.3%47% - 67.6%

#13 · glm-5.1

VALS-AI · Jun 17, 2026

Source label: zai/glm-5.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 55.6%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Zhipu AI.

56.9%54.3% - 59.6%

#14 · GPT-5.4 mini

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.4-mini-2026-03-17

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 51.9%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: OpenAI.

54.7%45.8% - 63.6%

#15 · Gemini 3 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-3-flash-preview

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 48.1%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

53.9%51.4% - 56.5%

#16 · kimi-k2.6

VALS-AI · Jun 17, 2026

Source label: kimi/kimi-k2.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 44.4%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Moonshot AI.

53.6%49.5% - 57.6%

#17 · minimax-m3

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 44.4%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: MiniMax.

53.6%52.1% - 55%

#18 · qwen3.6-plus

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.6-plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 37%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Alibaba.

53.2%50% - 56.4%

#19 · qwen3.7-plus

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.7-plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 33.3%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Alibaba.

52.8%51.5% - 54.1%

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

VALS-AI · Jun 17, 2026

Source label: nvidia/nemotron-3-ultra-550b-a55b

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 29.6%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Nvidia.

50.9%45.2% - 56.7%

#21 · deepseek-v4-pro

VALS-AI · Jun 17, 2026

Source label: deepseek/deepseek-v4-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 25.9%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: DeepSeek.

50.2%47.3% - 53.1%

#22 · minimax-m2.7

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M2.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 22.2%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: MiniMax.

48.7%42.7% - 54.7%

#23 · Grok 4.20

VALS-AI · Jun 17, 2026

Source label: grok/grok-4.20-0309-reasoning

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 18.5%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: xAI.

44.2%42.3% - 46.1%

#24 · Claude Haiku 4.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 14.8%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

43.8%40% - 47.6%

#25 · Grok 4.3

VALS-AI · Jun 17, 2026

Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 11.1%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: xAI.

41.9%36.8% - 47.1%

#26 · GPT-5.4 nano

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.4-nano-2026-03-17

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 7.4%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: OpenAI.

41.6%35.7% - 47.4%

#27 · mistral-medium-3.5

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-medium-3.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 3.7%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Mistral AI.

39%33.7% - 44.2%

#28 · Gemini 3.1 Flash-Lite Preview

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 0%
Last updated: aging
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

34.1%32.1% - 36%

Benchmarks · /benchmarks/vals-ai-terminal-bench-2-1

Terminal-Bench 2.1

Terminal-Bench 2.1 result as reported by Vals AI.

Source · Vals AI
Version · vals-ai snapshot 2026-06-24
Scores · 28

Test details

Verified but agingThis is an objective signal, so it is mainly about measurable task performance rather than public taste.

source

Vals AI

metric

Accuracy (%)

judge

Objective

direction

higher better

group id

vals_terminal_bench_2_1_current

domain

Coding

What it measures vs what it misses

✓ Measures

Difficult terminal-based agent tasks.

✗ Misses

Adjacent skills outside the benchmark task mix, latency, and cost.

Leaderboard · this benchmark version

#1 · Claude Fable 5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 100%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

80.5%77.9% - 83.2%

#2 · GPT-5.5

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 96.3%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: OpenAI.

76.4%75.1% - 77.7%

#3 · Gemini 3.5 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 92.6%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

74.2%72% - 76.4%

#4 · Claude Opus 4.8

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 88.9%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

71.9%70.6% - 73.2%

#5 · Gemini 3.1 Pro Preview

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.1-pro-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 85.2%
Last updated: aging
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

70.8%68.6% - 73%

#6 · Claude Opus 4.7

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 81.5%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

68.5%66% - 71.1%

#7 · glm-5.2-max

VALS-AI · Jun 17, 2026

Source label: zai/glm-5.2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 77.8%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Zhipu AI.

67.8%65.8% - 69.7%

#8 · kimi-k2.7-code

VALS-AI · Jun 17, 2026

Source label: kimi/kimi-k2.7-code

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 74.1%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Moonshot AI.

67%66.3% - 67.8%

#9 · Qwen3.7 Max

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.7-max

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 70.4%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Alibaba.

61%60.3% - 61.8%

#10 · mimo-v2.5

VALS-AI · Jun 17, 2026

Source label: xiaomi/mimo-v2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 66.7%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Xiaomi.

60.7%50.5% - 70.9%

#11 · Claude Sonnet 4.6

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-sonnet-4-6

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 63%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

57.3%56% - 58.6%

#12 · mimo-v2.5-pro

VALS-AI · Jun 17, 2026

Source label: xiaomi/mimo-v2.5-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 63%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Xiaomi.

57.3%47% - 67.6%

#13 · glm-5.1

VALS-AI · Jun 17, 2026

Source label: zai/glm-5.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 55.6%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Zhipu AI.

56.9%54.3% - 59.6%

#14 · GPT-5.4 mini

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.4-mini-2026-03-17

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 51.9%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: OpenAI.

54.7%45.8% - 63.6%

#15 · Gemini 3 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-3-flash-preview

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 48.1%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

53.9%51.4% - 56.5%

#16 · kimi-k2.6

VALS-AI · Jun 17, 2026

Source label: kimi/kimi-k2.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 44.4%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Moonshot AI.

53.6%49.5% - 57.6%

#17 · minimax-m3

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 44.4%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: MiniMax.

53.6%52.1% - 55%

#18 · qwen3.6-plus

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.6-plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 37%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Alibaba.

53.2%50% - 56.4%

#19 · qwen3.7-plus

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.7-plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 33.3%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Alibaba.

52.8%51.5% - 54.1%

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

VALS-AI · Jun 17, 2026

Source label: nvidia/nemotron-3-ultra-550b-a55b

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 29.6%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Nvidia.

50.9%45.2% - 56.7%

#21 · deepseek-v4-pro

VALS-AI · Jun 17, 2026

Source label: deepseek/deepseek-v4-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 25.9%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: DeepSeek.

50.2%47.3% - 53.1%

#22 · minimax-m2.7

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M2.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 22.2%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: MiniMax.

48.7%42.7% - 54.7%

#23 · Grok 4.20

VALS-AI · Jun 17, 2026

Source label: grok/grok-4.20-0309-reasoning

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 18.5%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: xAI.

44.2%42.3% - 46.1%

#24 · Claude Haiku 4.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 14.8%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

43.8%40% - 47.6%

#25 · Grok 4.3

VALS-AI · Jun 17, 2026

Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 11.1%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: xAI.

41.9%36.8% - 47.1%

#26 · GPT-5.4 nano

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.4-nano-2026-03-17

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 7.4%
Last updated: aging
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: OpenAI.

41.6%35.7% - 47.4%

#27 · mistral-medium-3.5

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-medium-3.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 3.7%
Last updated: aging
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Mistral AI.

39%33.7% - 44.2%

#28 · Gemini 3.1 Flash-Lite Preview

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/terminal-bench-2-1
Percentile: 0%
Last updated: aging
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

34.1%32.1% - 36%

Terminal-Bench 2.1

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version

Loading benchmark evidence.

Terminal-Bench 2.1

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version