List your company

Terminal Task Execution on Terminal-Bench 1.0

51AccuracyClaude Sonnet 4.5
15.74424.89734.0543.203Apr 28, 2026

Evaluation results

MethodLinks
Claude Sonnet 4.5Model Category=Proprietary, Scaffold=Terminus 22026.0451
Claude Opus 4.1Model Category=Proprietary, Scaffold=Terminus 22026.0443.8
Claude Haiku 4.5Model Category=Proprietary, Scaffold=Terminus 22026.0441.8
GPT-5Model Category=Proprietary, Scaffold=Terminus 22026.0441.3
Claude Opus 4Model Category=Proprietary, Scaffold=Terminus 22026.0439
Grok 4Model Category=Open-Source, Scaffold=Terminus 22026.0439
Claude Sonnet 4Model Category=Proprietary, Scaffold=Terminus 22026.0436.4
Qwen3-32B + SSModel Category=Open-Source, Scaffold=Terminus 2, Training Trajectories=SkillSynth2026.0433.8
Grok 4 FastModel Category=Open-Source, Scaffold=Terminus 22026.0431.3
GPT-5-MiniModel Category=Proprietary, Scaffold=Terminus 22026.0430.8
Qwen3-14B + SSModel Category=Open-Source, Scaffold=Terminus 2, Training Trajectories=SkillSynth2026.0422.9
Qwen3-8B + SSModel Category=Open-Source, Scaffold=Terminus 2, Training Trajectories=SkillSynth2026.0417.1