STEM on MGSM Zh
69.7Pass@1Qwen3
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3Size=4B, Type=Base, Prompt Setting=8-shot2025.12 | 69.7 | |
| Youtu-LLMSize=2B, Type=Base, Prompt Setting=8-shot2025.12 | 68.9 | |
| Qwen3Size=1.7B, Type=Base, Prompt Setting=8-shot2025.12 | 57.1 | |
| SmolLM3Size=3B, Type=Base, Prompt Setting=8-shot2025.12 | 40.7 | |
| Llama3.1Size=8B, Type=Base, Prompt Setting=8-shot2025.12 | 35.9 | |
| Gemma3Size=4B, Type=Base, Prompt Setting=8-shot2025.12 | 33 |