List your company

Terminal Task Execution on Terminal-Bench 1.0 (test)

34.9Avg Pass RateSkillFlow-specific
18.15622.50326.8531.197Apr 8, 2025May 28, 2025Jul 18, 2025Sep 7, 2025Oct 27, 2025Dec 17, 2025Feb 6, 2026

Evaluation results

MethodLinks
SkillFlow-specificSkillset=SkillFlow-specific2025.0434.924.20.035
No SkillsSkillset=No Skills2025.0434.821.10.03
VercelSkillset=Vercel2025.0432.621.20.031
SkillFlowSkillset=SkillFlow2025.0431.8230.034
ReptileBase Model=Devstral-2505-22B, Category=Fine-tuned Models2026.0218.9——
Terminus 2Base Model=LiteCoder-30a3b, Category=Fine-tuned Models2026.0218.8——