Mathematical Dialogue on MathChat
77.87Normalized ScoreDeepSeek-V3.2
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DeepSeek-V3.2formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 77.87 | 9 | |
| Qwen3-Max-Thinkingformatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 77.43 | 9 | |
| MiniMax-M2.5formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 69.58 | 9 | |
| GLM-5formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 67.65 | 9 | |
| Kimi-K2.5formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 61.41 | 9 |