Agentic Skill-Use No Skills Evaluation
24Final ScoreGPT-5.5
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.52026.07 | 24 | |
| Opus-4.72026.07 | 18 | |
| Gemini-3.1-Pro2026.07 | 16 | |
| Kimi-K2.62026.07 | 16 | |
| DeepSeek-V4-Flash2026.07 | 10 | |
| Qwen3.5Parameters=9B2026.07 | 2 | |
| Qwen3.5Parameters=4B2026.07 | 0 |