List your company

Agentic Skill-Use on Agentic Skill-Use Gold + Distr.

80Final Success RateOpus-4.7
5.1224.564463.44Jul 2, 2026

Evaluation results

MethodLinks
Opus-4.72026.07809077.289.790
GPT-5.52026.07769671.893.184
Gemini-3.1-Pro2026.07707882.789.770
Kimi-K2.62026.07548672.786.286
DeepSeek-V4-Flash2026.07266639.662.186
Qwen3.5Parameters=9B2026.07144444.534.534
Qwen3.5Parameters=4B2026.0784436.741.438