Terminal-Bench

terminal-bench@2.0 Leaderboard

Note: submissions may not modify timeouts or resources

harbor run -d terminal-bench@2.0 -a "agent" -m "model" -k 5

Note: submissions may not modify timeouts or resources

harbor run -d terminal-bench@2.0 --agent-import-path "path.to.agent:SomeAgent" -k 5

Showing 33 entries

Terminus 2

Select models

Select organizations

Rank	Agent	Model	Date	Agent Org	Model Org	Accuracy
24	Terminus 2	GPT-5.3-Codex	2026-02-05	AfterQuery	OpenAI	64.7%± 2.7
27	Terminus 2	Claude Opus 4.6	2026-02-06	AfterQuery	Anthropic	62.9%± 2.7
41	Terminus 2	Claude Opus 4.5	2025-11-22	AfterQuery	Anthropic	57.8%± 2.5
43	Terminus 2	Gemini 3 Pro	2025-11-21	AfterQuery	Google	56.9%± 2.5
46	Terminus 2	GPT-5.2	2025-12-12	AfterQuery	OpenAI	54.0%± 2.9
48	Terminus 2	GLM 5	2026-02-23	AfterQuery	Z-AI	52.4%± 2.6
52	Terminus 2	Gemini 3 Flash	2026-01-07	AfterQuery	Google	51.7%± 3.1
55	Terminus 2	GPT-5.1	2025-11-16	AfterQuery	OpenAI	47.6%± 2.8
60	Terminus 2	GPT-5-Codex	2025-10-31	AfterQuery	OpenAI	43.4%± 2.9
61	Terminus 2	Kimi K2.5	2026-02-04	AfterQuery	Kimi	43.2%± 2.9
64	Terminus 2	Claude Sonnet 4.5	2025-10-31	AfterQuery	Anthropic	42.8%± 2.8
69	Terminus 2	Minimax m2.5	2026-02-23	AfterQuery	Minimax	42.2%± 2.6
72	Terminus 2	DeepSeek-V3.2	2026-02-10	AfterQuery	DeepSeek	39.6%± 2.8
73	Terminus 2	Claude Opus 4.1	2025-10-31	AfterQuery	Anthropic	38.0%± 2.6
75	Terminus 2	GPT-5.1-Codex	2025-11-17	AfterQuery	OpenAI	36.9%± 3.2
77	Terminus 2	Kimi K2 Thinking	2025-11-11	AfterQuery	Moonshot AI	35.7%± 2.8
79	Terminus 2	GPT-5	2025-10-31	AfterQuery	OpenAI	35.2%± 3.1
84	Terminus 2	GLM 4.7	2026-01-28	AfterQuery	Z-AI	33.4%± 2.8
86	Terminus 2	Gemini 2.5 Pro	2025-10-31	AfterQuery	Google	32.6%± 3.0
88	Terminus 2	MiniMax M2	2025-11-01	AfterQuery	MiniMax	30.0%± 2.7
90	Terminus 2	MiniMax M2.1	2025-12-23	AfterQuery	MiniMax	29.2%± 2.9
92	Terminus 2	Claude Haiku 4.5	2025-10-31	AfterQuery	Anthropic	28.3%± 2.9
93	Terminus 2	Kimi K2 Instruct	2025-11-01	AfterQuery	Moonshot AI	27.8%± 2.5
102	Terminus 2	GLM 4.6	2025-11-01	AfterQuery	Z.ai	24.5%± 2.4
103	Terminus 2	GPT-5-Mini	2025-10-31	AfterQuery	OpenAI	24.0%± 2.5
104	Terminus 2	Qwen 3 Coder 480B	2025-11-01	AfterQuery	Alibaba	23.9%± 2.8
105	Terminus 2	Grok 4	2025-10-31	AfterQuery	xAI	23.1%± 2.9
108	Terminus 2	GPT-OSS-120B	2025-11-01	AfterQuery	OpenAI	18.7%± 2.7
110	Terminus 2	AfterQuery-GPT-OSS-20B	2026-03-31	AfterQuery	AfterQuery	17.0%± 2.5
111	Terminus 2	Gemini 2.5 Flash	2025-10-31	AfterQuery	Google	16.9%± 2.4
115	Terminus 2	Grok Code Fast 1	2025-10-31	AfterQuery	xAI	14.2%± 2.5
120	Terminus 2	GPT-5-Nano	2025-10-31	AfterQuery	OpenAI	7.9%± 1.9
123	Terminus 2	GPT-OSS-20B	2025-11-01	AfterQuery	OpenAI	3.1%± 1.5

Results in this leaderboard correspond to terminal-bench@2.0.

Submission instructions can be found at harborframework/terminal-bench-2-leaderboard

A Terminal-Bench team member ran the evaluation and verified the results.

Displaying 33 of 123 available entries