Skip to main content
Evaluation sources/Terminal-Bench
ObservingCoding

Terminal-Bench

Terminal-Bench · Public model evaluation results from Terminal-Bench.

Official evaluation
Source description

This source measures concrete delivery performance in Coding; 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

GPT-5.6 Sol88.888.82026-07-09
Claude Fable 58888.02026-06-09
GPT-5.6 Terra87.487.42026-07-09
GPT-5.6 Luna84.784.72026-07-09
GPT-5.584.184.12026-08-05
Grok 4.583.383.32026-07-08
GPT-5.582.782.72026-04-23
GLM-5.282.782.72026-06-16
Claude Sonnet 580.480.42026-06-30
Muse Spark 1.18080.02026-07-09
GPT-5.578.278.22026-05-28
GPT-5.575.875.82026-08-05
GPT-5.475.175.12026-04-23
Claude Opus 4.874.674.62026-05-28
Claude Opus 4.773.873.82026-08-05
GPT-5.573.473.42026-08-05
Claude Opus 4.771.471.42026-08-05
LongCat-2.070.870.82026-06-30
Claude Opus 4.770.670.62026-08-05
Gemini 3.1 Pro Preview70.370.32026-05-28
Claude Opus 4.670.270.22026-08-05
GPT-5.469.869.82026-08-05
Qwen3.7 Max69.769.72026-05-19
Gemini 3.1 Pro Preview68.368.32026-08-05
Claude Sonnet 4.66767.02026-06-30
Claude Opus 4.766.166.12026-05-28
MiniMax-M36666.02026-06-01
GLM-5.165.165.12026-08-05
GPT-5.464.764.72026-08-05
DeepSeek V4 Pro64.764.72026-08-05
Kimi K2.664.364.32026-08-05
Claude Sonnet 4.663.163.12026-08-05
Step 3.7 Flash59.659.62026-05-29
Nemotron 3 Ultra 550B A55B56.456.42026-06-04
MAI-Code-1-Flash54.854.82026-08-05
MiniMax-M2.751.151.12026-06-01
Laguna XS 2.137.537.52026-07-02

Frequently asked questions