Mathematical Reasoning on GSM8K (P@4, #Tok)
94.5Pass@4
Vanilla LLM
Updated 22d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 94.5 | 2,100 | |
2026.05 | 94.3 | 1,700 | |
2026.05 | 94.2 | 1,400 | |
2026.05 | 94.1 | 1,200 | |
2026.05 | 52 | 1,200 | |
2026.05 | 42.8 | 600 |
Vanilla LLM
| Method | Links | ||
|---|---|---|---|
2026.05 | 94.5 | 2,100 | |
2026.05 | 94.3 | 1,700 | |
2026.05 | 94.2 | 1,400 | |
2026.05 | 94.1 | 1,200 | |
2026.05 | 52 | 1,200 | |
2026.05 | 42.8 | 600 |