Agentic Tool Use on Tool-Decathlon
46.3Score
GPT-5.2 (xhigh)
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 46.3 | |
2026.02 | 43.5 | |
2026.02 | 39.2 | |
2026.02 | 36.4 | |
2026.02 | 35.2 | |
2026.02 | 27.8 | |
2026.02 | 23.8 |
GPT-5.2 (xhigh)
| Method | Links | |
|---|---|---|
2026.02 | 46.3 | |
2026.02 | 43.5 | |
2026.02 | 39.2 | |
2026.02 | 36.4 | |
2026.02 | 35.2 | |
2026.02 | 27.8 | |
2026.02 | 23.8 |