Mathematical Reasoning on GSM8K (PR, Faithfulness, AUROC, Step Analysis)
0.6Performance Ratio (PR)
GRPO Baseline
Updated 21d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.05 | 0.6 | - | 99.4 | 77.8 | 0.924 | 2,351 | |
2026.05 | 0 | 100 | 100 | 83 | - | 1,895 |
GRPO Baseline
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.05 | 0.6 | - | 99.4 | 77.8 | 0.924 | 2,351 | |
2026.05 | 0 | 100 | 100 | 83 | - | 1,895 |