List your company

Agentic Skill-Use on Agentic Skill-Use Gold Skills

88Final ScoreOpus-4.7
4.826.44869.6Jul 2, 2026

Evaluation results

MethodLinks
Opus-4.72026.078810086.510090
GPT-5.52026.07801008096.6100
Gemini-3.1-Pro2026.07729872.682.890
Kimi-K2.62026.07669284.293.188
DeepSeek-V4-Flash2026.07328840.168.972
Qwen3.5Parameters=9B2026.07189247.248.376
Qwen3.5Parameters=4B2026.0788039.544.864