Evaluation sources/Terminal-Bench 4.0 (Vals rerun)

ParticipatingCoding

Terminal-Bench 4.0 (Vals rerun)

Vals AI · Public model evaluation results from Terminal-Bench 4.0 (Vals rerun).

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


Claude Opus 5.5	65.15	79.6	2026-11-05
Claude Sonnet 5.5	64.14	78.7	2026-11-05
GPT-6 Astra	59.6	75.1	2026-11-05
Claude Fable 5.1	58.08	73.9	2026-11-05
Gemini 4 Argon	57.58	73.5	2026-11-05
GPT-6.1 Sol	55.05	71.4	2026-11-05
Claude Opus 5	53.53	70.2	2026-11-05
GPT-6.1 Terra	49.49	67.0	2026-11-05
GPT-6 Sol	44.44	62.9	2026-11-05
Claude Fable 5	41.41	60.5	2026-11-05
GLM 5.3	38.89	58.4	2026-11-05
GPT-5.6 Sol	37.88	57.6	2026-11-05
GLM-5.3 Flash	37.37	57.2	2026-11-05
GLM-5.3 Flash	37.37	57.2	2026-10-18
GLM-5.3 Flash	37.37	57.2	2026-10-17
Claude Haiku 5.5	36.36	56.4	2026-11-05
Qwen3.8 Max	34.34	54.8	2026-11-05
DeepSeek V4.1 Flash 1017	31.82	52.7	2026-11-05
Step 5 Preview	31.82	52.7	2026-11-05
MiMo V2.6 Pro	31.31	52.3	2026-11-05
Grok 4.7	28.79	50.3	2026-11-05
Mistral Large 4	26.26	48.3	2026-11-05
MiniMax M3.1 Flash	25.25	47.5	2026-11-05
Muse Spark 1.3	24.75	47.0	2026-11-05
MiMo V2.6 Flash	24.24	46.6	2026-10-18
MiMo V2.6 Flash	24.24	46.6	2026-11-05
MiMo V2.6 Flash	24.24	46.6	2026-10-17
Claude Opus 4.8	23.23	45.8	2026-11-05
GPT-5.6 Terra	22.73	45.4	2026-11-05
Gemini 3.8 Flash	19.7	43.0	2026-11-05
DeepSeek V4.1 Flash	19.7	43.0	2026-11-05
DeepSeek V4 Flash 0731	18.69	42.2	2026-11-05
Kimi K3	17.17	41.0	2026-11-05
Grok 4.6	17.17	41.0	2026-11-05
DeepSeek V4 Pro 0813	14.14	38.5	2026-11-05
GPT-6 Luna	13.64	38.1	2026-11-05
GPT-5.6 Luna	11.62	36.5	2026-11-05
Claude Sonnet 5	10.61	35.7	2026-11-05
Grok 4.5	8.59	34.0	2026-11-05
Muse Spark 1.2	6.06	32.0	2026-11-05
GPT-5.4 mini	2.52	29.2	2026-11-05
MiniMax-M3	1.01	27.9	2026-11-05
MiMo-V2.5-Pro	0.51	27.5	2026-11-05
Inkling	0.51	27.5	2026-11-05
Inkling Small	0	27.1	2026-11-05

Frequently asked questions