General Reasoning on Average Overall
71.3P@4MPD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MPD2026.05 | 71.3 | 6,100 | |
| CRISP2026.05 | 70.7 | 7,600 | |
| Direct Comp.2026.05 | 68.9 | 6,900 | |
| Vanilla LLM2026.05 | 68.2 | 8,200 | |
| LiteCoT2026.05 | 56.8 | 7,300 | |
| Chain-of-Draft2026.05 | 55.1 | 5,900 |
| Method | Links | ||
|---|---|---|---|
| MPD2026.05 | 71.3 | 6,100 | |
| CRISP2026.05 | 70.7 | 7,600 | |
| Direct Comp.2026.05 | 68.9 | 6,900 | |
| Vanilla LLM2026.05 | 68.2 | 8,200 | |
| LiteCoT2026.05 | 56.8 | 7,300 | |
| Chain-of-Draft2026.05 | 55.1 | 5,900 |