Agentic Reasoning on ALFWorld (Detailed Metrics)
91Success Rate (Org.)
CAMEL
Updated 22d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 91 | 22.9 | 38.3 | 15.8 | |
2026.05 | 86.4 | 35.6 | 41.7 | 28.4 | |
2026.05 | 84.1 | 39.7 | 54.8 | 31.6 | |
2026.05 | 83.4 | 41.9 | 57.6 | 34.2 | |
2026.05 | 83.2 | 27.2 | 42.5 | 20.3 | |
2026.05 | 77.8 | 48.4 | 52.6 | 39.8 | |
2026.05 | 72.6 | 42.4 | 62.1 | 33.7 | |
2026.05 | 72.4 | 43.8 | 58.4 | 35.9 | |
2026.05 | 71.6 | 46.2 | 61.8 | 38.7 | |
2026.05 | 67.4 | 17.4 | 34.6 | 11.3 | |
2026.05 | 66 | 12.7 | 29 | 6.5 | |
2026.05 | 65.1 | 52.4 | 67.1 | 44.2 | |
2026.05 | 63.7 | 25.4 | 42.6 | 15.8 | |
2026.05 | 62.2 | 30.3 | 44.7 | 25.7 | |
2026.05 | 60.4 | 34.2 | 48.6 | 24.3 | |
2026.05 | 59.8 | 28.5 | 44.1 | 14.3 | |
2026.05 | 59.8 | 36.4 | 53.9 | 29.7 | |
2026.05 | 58.4 | 31.7 | 48.3 | 24.9 | |
2026.05 | 54.1 | 39.3 | 50.7 | 22.6 | |
2026.05 | 52.5 | 41.1 | 50.8 | 32.4 |