Terminal-Bench 2.0 leaderboard

A benchmark for agentic software engineering tasks executed in real terminal environments. Models must inspect files, run commands, edit code, and recover from errors over multi-step workflows.

Models ranked by their published Terminal-Bench 2.0 value

Rank	Model	Provider	Interactive CLI agent evaluation
1	GPT-5.6 Sol	OpenAI	91.9
2	Kimi K3	Moonshot AI	88.3
3	Claude Mythos 5	Anthropic	88
4	GPT-5.6 Terra	OpenAI	87.4
5	GPT-5.6 Luna	OpenAI	84.7
6	Claude Fable 5	Anthropic	84.3
7	Grok 4.5	xAI	83.3
8	SASakana Fugu-Ultra	Sakana AI	82.1
9	GPT-5.5	OpenAI	82
10	SWE-1.7	Cognition	81.5
11	GLM-5.2	Z.AI	81
12	Claude Sonnet 5	Anthropic	80.4
13	SASakana Fugu	Sakana AI	80.2
14	Muse Spark 1.1	Meta	80
15	DAOrnith-1.0-397B	DeepReinforce AI	77.5
16	GPT-5.3 Codex	OpenAI	77.3
17	Gemini 3.5 Flash	Google	76.2
18	GPT-5.4	OpenAI	75.1
19	Claude Opus 4.8	Anthropic	74.6
20	Qwen3.7 Plus	Alibaba	70.3
21	Laguna S 2.1	Poolside	70.2
22	Qwen3.7 Max	Alibaba	69.7
23	Claude Opus 4.7 (Adaptive)	Anthropic	69.4
24	Composer 2.5	Cursor	69.3
25	MiMo-V2.5-Pro	Xiaomi	68.4
26	DeepSeek V4 Pro 0813	DeepSeek	67.9
27	Kimi K2.6	Moonshot AI	66.7
28	MiniMax M3	MiniMax	66
29	MiMo-V2.5	Xiaomi	65.8
30	Claude Opus 4.6	Anthropic	65.4
30	Qwen 3.6 Max (preview)	Alibaba	65.4
32	TMInkling-Small	Thinking Machines Lab	64.7
33	DAOrnith-1.0-35B	DeepReinforce AI	64.2
34	TMInkling	Thinking Machines Lab	63.8
35	GLM-5.1	Z.AI	63.5
36	Composer 2	Cursor	61.7
37	Qwen3.6 Plus	Alibaba	61.6
38	GPT-5.4 mini	OpenAI	60
39	Step 3.7 Flash	StepFun	59.5
40	Claude Opus 4.5	Anthropic	59.3
40	Qwen3.6-27B	Alibaba	59.3
42	Claude Sonnet 4.6	Anthropic	59.1
43	Muse Spark	Meta	59
44	MiniMax M2.7	MiniMax	57
45	DeepSeek V4 Flash 0731	DeepSeek	56.9
46	Nemotron 3 Ultra	NVIDIA	56.4
47	GLM-5	Z.AI	56.2
48	Hy3 Preview	Tencent	54.4
49	Gemini 3.5 Flash-Lite	Google	54
50	Qwen3.5 397B	Alibaba	52.5
51	Qwen3.6-35B-A3B	Alibaba	51.5
52	Kimi K2.5	Moonshot AI	50.8
52	Kimi K2.5 (Reasoning)	Moonshot AI	50.8
54	Claude Sonnet 4.5	Anthropic	50
55	Qwen3.5-122B-A10B	Alibaba	49.4
56	Grok 4.20	xAI	47.1
57	GPT-5.4 nano	OpenAI	46.3
58	MAI-Thinking-1	Microsoft	46
59	Laguna M.1	Poolside	45.8
60	DAOrnith-1.0-9B	DeepReinforce AI	43.1
61	Qwen3.5-27B	Alibaba	41.6
62	GLM-4.7	Z.AI	41
63	Qwen3.5-35B-A3B	Alibaba	40.5
64	Laguna XS 2.1	Poolside	37.5
65	Laguna XS.2	Poolside	35.7
66	LongCat-Flash-Lite-Sparse	Meituan	33.7
67	Nemotron 3.5 Lightning 30B A3B NVFP4	NVIDIA	23.46

Evidence key: Observed

Rows are ordered by the value Terminal-Bench 2.0 published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.