Language Understanding on SuperBLUE
0.61MA.
PROBELLM
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 0.61 | 0.39 | 0.75 | |
2026.02 | 0.59 | 0.41 | 0.44 | |
2026.02 | 0.58 | 0.42 | 0.59 | |
2026.02 | 0.58 | 0.42 | 0.69 | |
2026.02 | 0.53 | 0.47 | 0.5 | |
2026.02 | 0.53 | 0.47 | 0.65 | |
2026.02 | 0.5 | 0.5 | 0.39 | |
2026.02 | 0.48 | 0.52 | 0.65 | |
2026.02 | 0.48 | 0.52 | 0.31 | |
2026.02 | 0.46 | 0.54 | 0.71 | |
2026.02 | 0.45 | 0.55 | 0.46 | |
2026.02 | 0.34 | 0.66 | 0.43 |