Reasoning on MuSR (Score, Delta, Avg. Rank)
56.48MuSR ScoreQwen2.5(14B)T
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Qwen2.5(14B)TEvaluation Protocol=Generation-based2026.07 | 56.48 | — | — | |
| RG-OPDEvaluation Protocol=Generation-based2026.07 | 44.89 | 1.81 | 2 | |
| Reverse KLEvaluation Protocol=Generation-based2026.07 | 44.66 | 1.58 | 3 | |
| Qwen2.5(1.5B)SEvaluation Protocol=Generation-based2026.07 | 43.08 | 0 | 2.4 | |
| TSD-KDEvaluation Protocol=Generation-based2026.07 | 42.46 | -0.62 | 2.6 | |
| Qwen2.5(14B)TEvaluation Protocol=Likelihood-based2026.07 | 41.01 | — | — | |
| TSD-KDEvaluation Protocol=Likelihood-based2026.07 | 39.81 | 2.91 | 2.6 | |
| RG-OPDEvaluation Protocol=Likelihood-based2026.07 | 37.83 | 0.93 | 2 | |
| Qwen2.5(1.5B)SEvaluation Protocol=Likelihood-based2026.07 | 36.9 | 0 | 2.4 | |
| Reverse KLEvaluation Protocol=Likelihood-based2026.07 | 35.85 | -1.05 | 3 |