List your company

Agentic Terminal Tasks on Terminal-Bench (test)

48.75Success RateClaude Opus 4.5
11.0520.837530.62540.4125Feb 3, 2026

Evaluation results

MethodLinks
Claude Opus 4.5Base Model=Claude Opus 4.52026.0248.75
Claude Sonnet 4.5Base Model=Claude Sonnet 4.52026.0245
MiniMax-M2Base Model=MiniMax-M22026.0237.5
Qwen 3 Coder 480BBase Model=Qwen 3 Coder 480B2026.0236.25
Claude Sonnet 4Base Model=Claude Sonnet 42026.0233.75
Qwen3-32B + CVE-Factory (3k)Fine-tuning Data Source=CVE-Factory, Training Data Scale (Trajectories)=3k, Base Model=Qwen3-32B2026.0231.25
Qwen3-32B + CVE-Factory (4k)Fine-tuning Data Source=CVE-Factory, Training Data Scale (Trajectories)=4k, Base Model=Qwen3-32B2026.0228.75
Qwen3-32B + SETAFine-tuning Data Source=SETA, Training Data Scale (Trajectories)=4k, Base Model=Qwen3-32B2026.0227.5
Qwen3-Coder-30BBase Model=Qwen3-Coder-30B2026.0213.75
Qwen3-32BBase Model=Qwen3-32B2026.0212.5