Agentic Reasoning on ScienceWorld
82.2Original Score
CAMEL
Updated 22d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 82.2 | 10.4 | 35.8 | 23.4 | |
2026.05 | 79.4 | 16.3 | 44.1 | 30.3 | |
2026.05 | 74.6 | 27.4 | 55.1 | 41.8 | |
2026.05 | 74.6 | 23.1 | 46.3 | 45.4 | |
2026.05 | 73.8 | 12.5 | 40.4 | 25.9 | |
2026.05 | 73.1 | 28.7 | 47.2 | 43.2 | |
2026.05 | 71.8 | 35.3 | 63.4 | 48.7 | |
2026.05 | 70.8 | 24.1 | 50.6 | 36.5 | |
2026.05 | 69.4 | 36.8 | 61.2 | 49.3 | |
2026.05 | 69.1 | 30.2 | 57.4 | 37.8 | |
2026.05 | 69.1 | 23.6 | 56.3 | 37.8 | |
2026.05 | 68.3 | 33.8 | 56.4 | 40.7 | |
2026.05 | 66.2 | 31.5 | 59.7 | 44.3 | |
2026.05 | 65.2 | 35.8 | 49.7 | 49.1 | |
2026.05 | 64 | 30.8 | 58 | 44.7 | |
2026.05 | 62.8 | 34.8 | 60.1 | 42.3 | |
2026.05 | 58.2 | 42.8 | 70.1 | 56.4 | |
2026.05 | 57.2 | 47.1 | 74.6 | 60.3 | |
2026.05 | 56.4 | 49.8 | 77.3 | 63.1 | |
2026.05 | 54.1 | 51.2 | 78.6 | 60.4 |