Problem Generation on KMP-Gen
86.3Follow-up ScoreQwen2.5-Math-72B-Inst
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen2.5-Math-72B-InstSize=72B2026.03 | 86.3 | 82.6 | |
| Qwen2.5-72B-InstSize=72B2026.03 | 81.3 | 78.1 | |
| KMP-LM-7BSize=7B2026.03 | 81.1 | 83.2 | |
| LearnLM-1.5-ProSize=-2026.03 | 77 | 75 | |
| GPT-4o miniSize=-2026.03 | 76.5 | 64.8 | |
| Gemini 2.0 FlashSize=-2026.03 | 75 | 73.2 | |
| GPT-4oSize=-2026.03 | 74.8 | 72.2 | |
| MathChatsync-LLMSize=7B2026.03 | 70.9 | 71.3 | |
| Qwen2.5-7B-InstSize=7B2026.03 | 66.2 | 66.2 | |
| TutorChat-LLMSize=7B2026.03 | 65.8 | 69.5 | |
| Qwen2.5-Math-7B-InstSize=7B2026.03 | 48.6 | 52.8 | |
| Llama-3.1-8B-InstSize=8B2026.03 | 41.7 | 38.5 |