Skip to main content
Evaluation sources/Terminal-Bench Science · AA
ParticipatingReasoning

Terminal-Bench Science · AA

Artificial Analysis · Public model evaluation results from Terminal-Bench Science · AA.

Official evaluation
Source description

This source measures concrete delivery performance in Reasoning; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Claude Fable 5.20.7333333388.02026-11-10
Gemini 4 Carbon0.6476190582.12026-11-11
GPT-6 Astra0.6333333381.12026-11-05
Claude Opus 5.50.6190476280.22026-11-05
GPT-6.1 Sol0.5809523877.52026-11-05
GPT-6.1 Terra0.5761904877.22026-11-05
Claude Sonnet 5.50.5333333374.32026-11-05
Gemini 4 Argon0.5285714373.92026-10-18
Gemini 4 Argon0.5285714373.92026-10-17
Gemini 4 Argon0.5285714373.92026-11-05
Claude Fable 5.10.4333333367.42026-11-05
Muse Wonder Full0.3714285763.22026-11-05
GPT-6 Sol0.358.22026-11-05
Claude Opus 50.2857142957.32026-11-05
Muse Wonder0.2571428655.32026-11-05
GPT-5.6 Sol0.2238095253.02026-11-05
Claude Haiku 5.50.251.42026-11-05
GPT-5.6 Terra0.1380952447.12026-11-05
DeepSeek V4.1 Flash 10170.1285714346.52026-11-05
Grok 4.70.1142857145.52026-11-05
Muse Spark 1.30.1095238145.22026-11-05
Gemini 3.8 Flash0.104761944.82026-11-05
Gemini 3.8 Flash0.144.52026-10-21
Grok 4.70.095238144.22026-11-02
Grok 4.70.095238144.22026-10-17
Grok 4.70.095238144.22026-10-18
GLM 5.30.095238144.22026-11-05
DeepSeek V4.1 Flash0.0904761943.82026-11-05
GPT-6 Luna0.0857142943.52026-11-05
Kimi K30.0809523843.22026-11-05
Grok 4.60.0619047641.92026-11-05
DeepSeek V4 Pro0.0571428641.62026-10-11
DeepSeek V4 Pro 08130.0571428641.62026-11-05
MiMo V2.6 Pro0.0571428641.62026-11-05
Mistral Large 40.0476190540.92026-10-28
GLM-5.3 Flash0.0476190540.92026-10-17
GLM-5.3 Flash0.0476190540.92026-11-05
GLM-5.3 Flash0.0476190540.92026-10-18
Mistral Large 40.0428571440.62026-11-05
MiMo V2.6 Flash0.0428571440.62026-10-18
MiMo V2.6 Flash0.0428571440.62026-10-17
MiMo V2.6 Flash0.0428571440.62026-11-05
Ling-3.1-flash-10190.0428571440.62026-11-05
GPT-5.6 Luna0.0333333339.92026-11-05
MiniMax M3.1 Flash0.0333333339.92026-11-05
Step 5 Preview0.0238095239.32026-11-05
MiniMax-M30.004761938.02026-11-05
Claude Haiku 4.5037.62026-11-05
Command A Plus037.62026-11-05
North Mini Code037.62026-11-05
Gemini 3.1 Flash Lite037.62026-11-05
Gemini 3.5 Flash Lite037.62026-11-05
Nemotron 3 Ultra 550B A55B037.62026-11-05
gpt-oss-120b037.62026-11-05
Inkling037.62026-11-05
Inkling Small037.62026-11-05
Mistral Medium 3.5037.62026-11-05

Frequently asked questions