List your company

Skill execution on SkillsBench

56.9Overall Success Rate (avg@5)Evolver
3.96417.70731.4545.193May 11, 2026May 14, 2026May 17, 2026May 21, 2026May 24, 2026May 27, 2026May 31, 2026

Evaluation results

MethodLinks
EvolverRefinement iterations (R)=22026.0556.950.463.883.97240608464—
Revision v3Model=GPT-5.5, Harness=Codex2026.0553————————25.58
EvolverRefinement iterations (R)=12026.0548.21858754023.3204546.7—
Revision v3Model=Opus-4.7, Harness=Claude Code2026.0544————————32.56
Human-curated skill2026.0543.638.85043.3403052.53262—
Revision v3Model=DeepSeek-V4-Pro, Harness=Claude Code2026.0541————————31.4
Revision v3Model=Kimi-2.6, Harness=Claude Code2026.0537————————30.23
Skill v0Model=GPT-5.5, Harness=Codex2026.0535————————4.65
Skill-CreatorModel=GPT-5.5, Harness=Codex2026.0534————————3.49
SkillCreator-SkillsBench2026.0533.98.65046.4252026.763.830—
Self-Gen2026.0532—————————
No skillModel=GPT-5.5, Harness=Codex2026.0531—————————
No skill2026.0529.93524.338.329.11527.53240—
Skill-CreatorModel=Opus-4.7, Harness=Claude Code2026.0528————————13.95
Revision v3Model=Qwen-3.6plus, Harness=Claude Code2026.0527————————24.42
Skill v0Model=DeepSeek-V4-Pro, Harness=Claude Code2026.0523————————10.47
Skill-CreatorModel=DeepSeek-V4-Pro, Harness=Claude Code2026.0521————————8.14
Skill v0Model=Kimi-2.6, Harness=Claude Code2026.0519————————9.3
Skill v0Model=Opus-4.7, Harness=Claude Code2026.0517————————1.16
Skill-CreatorModel=Kimi-2.6, Harness=Claude Code2026.0517————————6.98
No skillModel=Opus-4.7, Harness=Claude Code2026.0516—————————
No skillModel=DeepSeek-V4-Pro, Harness=Claude Code2026.0514—————————
No skillModel=Kimi-2.6, Harness=Claude Code2026.0511—————————
Skill v0Model=Qwen-3.6plus, Harness=Claude Code2026.059————————3.49
Skill-CreatorModel=Qwen-3.6plus, Harness=Claude Code2026.058————————2.33
No skillModel=Qwen-3.6plus, Harness=Claude Code2026.056—————————