Multistep Reasoning on MUSR-fr
33.79Average ScoreGamayun
Evaluation Results
| Method | Links | |
|---|---|---|
| GamayunZero-shot=true, Chat Template=true2025.12 | 33.79 | |
| EuroLMZero-shot=true, Chat Template=true2025.12 | 33.13 | |
| Llama3.2Zero-shot=true, Chat Template=true2025.12 | 31.94 | |
| Qwen2.5Zero-shot=true, Chat Template=true2025.12 | 30.99 | |
| Qwen3Zero-shot=true, Chat Template=true2025.12 | 28.86 | |
| Gemma3Zero-shot=true, Chat Template=true2025.12 | 28.73 |