Multistep Soft Reasoning on MuSR
69Accuracy
GPT-OSS-120B
Updated 16d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.04 | 69 | 12,700 | - | - | |
2026.04 | 64.83 | 7,195 | 3.81 | 46.38 | |
2026.04 | 62.45 | 13,419 | - | - | |
2026.04 | 59.5 | 5,994 | -13.77 | 52.8 | |
2026.04 | 50.65 | 1,328 | - | - | |
2026.04 | 37.41 | 25,600 | - | - | |
2026.04 | 34 | 5,912 | -9.12 | 76.91 | |
2026.04 | 29 | 1,603 | - | - | |
2026.04 | 10.33 | 1,061 | - | - |