Tool Creation and Reuse on Tool Creation and Reuse in Sensitive Tasks D_reuse (test)
56ASRGemini-3-Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-3-Pro2026.02 | 56 | |
| Seed-OSS-36B-Instruct2026.02 | 52 | |
| MiniMax-M2.12026.02 | 52 | |
| Grok-42026.02 | 48 | |
| Qwen3-max2026.02 | 44 | |
| Qwen3-235B-A22B-Thinking-2507Model Type=MoE, Mode=Thinking2026.02 | 44 | |
| GLM-4.72026.02 | 44 | |
| Claude Sonnet 4.5Mode=Thinking2026.02 | 40 | |
| Kimi-K2-Instruct-09052026.02 | 40 | |
| Doubao-seed-1-8-2512282026.02 | 32 | |
| GPT-5.2-2025-12-112026.02 | 24 |