Multi-step Mathematical Reasoning on MMLU (test)
90.84Accuracy
LLM-Debate
Updated 6d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 90.84 | 404.09 | |
2026.05 | 90.4 | 255.06 | |
2026.05 | 90.36 | 12.47 | |
2026.05 | 89.96 | 88.03 | |
2026.05 | 87.96 | 9.13 | |
2026.05 | 87.9 | 28.04 | |
2026.05 | 87.49 | 4.87 | |
2026.05 | 87.23 | 4.68 | |
2026.05 | 86.2 | 1.86 | |
2026.05 | 85.92 | 82.71 | |
2026.05 | 84.1 | 3.42 | |
2026.05 | 83.71 | 4.14 | |
2026.05 | 81.7 | 12.6 | |
2026.05 | 80.37 | 2.27 |