Quality Evaluation on Science reasoning tasks
38.5Param & Constraint Acc
Force Strong
Updated 3mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.01 | 38.5 | 28.8 | 19.2 | 9.4 | |
2026.01 | 38.2 | 29.5 | 18.2 | 9.9 | |
2026.01 | 35.2 | 27.5 | 16 | 9.8 |
Force Strong
| Method | Links | ||||
|---|---|---|---|---|---|
2026.01 | 38.5 | 28.8 | 19.2 | 9.4 | |
2026.01 | 38.2 | 29.5 | 18.2 | 9.9 | |
2026.01 | 35.2 | 27.5 | 16 | 9.8 |