Multi-Turn Problem Solving on KMP-FQA
91.2KMP-FQA ScoreGemini 2.0 Flash
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 2.0 FlashSize=-2026.03 | 91.2 | |
| Gemini 2.0 FlashSize=-2026.03 | 91.2 | |
| LearnLM-1.5-ProSize=-2026.03 | 87.7 | |
| LearnLM-1.5-ProSize=-2026.03 | 87.7 | |
| Phi-4Size=14B2026.03 | 85.6 | |
| GPT-4oSize=-2026.03 | 84.1 | |
| GPT-4oSize=-2026.03 | 84.1 | |
| Qwen2.5-Math-72B-InstSize=72B2026.03 | 83.2 | |
| Qwen2.5-Math-72B-InstSize=72B2026.03 | 83.2 | |
| Qwen2.5-32B-InstSize=32B2026.03 | 82.6 | |
| Qwen2.5-72B-InstSize=72B2026.03 | 82.2 | |
| Qwen2.5-72B-InstSize=72B2026.03 | 82.2 | |
| Qwen2.5-14B-InstSize=14B2026.03 | 81.4 | |
| GPT-4o miniSize=-2026.03 | 79.4 | |
| GPT-4o miniSize=-2026.03 | 79.4 | |
| KMP-LM-7BSize=7B2026.03 | 77.5 | |
| KMP-LM-7BSize=7B2026.03 | 77.5 | |
| Qwen2.5-Math-7B-InstSize=7B2026.03 | 76.1 | |
| Qwen2.5-Math-7B-InstSize=7B2026.03 | 76.1 | |
| Qwen2.5-7B-InstSize=7B2026.03 | 71 | |
| Qwen2.5-7B-InstSize=7B2026.03 | 71 | |
| TutorChat-LLMSize=7B2026.03 | 57.7 | |
| TutorChat-LLMSize=7B2026.03 | 57.7 | |
| MathChatsync-LLMSize=7B2026.03 | 53.5 | |
| MathChatsync-LLMSize=7B2026.03 | 53.5 | |
| Mistral-Nemo-InstSize=12B2026.03 | 50.2 | |
| Llama-3.1-8B-InstSize=8B2026.03 | 50.1 | |
| Llama-3.1-8B-InstSize=8B2026.03 | 50.1 |