Question Answering on PopQA (LLM Judge)
46.7LLM Judge ScoreQwen3-1.7B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3-1.7BBackbone=DeepSeek-V4-Flash, Evaluation Protocol=mean@42026.07 | 46.7 | |
| Qwen3-1.7B-SFTBackbone=GLM-5.1, Evaluation Protocol=mean@42026.07 | 46.33 | |
| Qwen3-1.7B-SFTBackbone=DeepSeek-V4-Flash, Evaluation Protocol=mean@42026.07 | 46.21 | |
| DeepSeek-V4-FlashBackbone=GLM-5.1, Evaluation Protocol=mean@42026.07 | 46.09 | |
| Qwen3-1.7BBackbone=GLM-5.1, Evaluation Protocol=mean@42026.07 | 45.97 | |
| DeepSeek-V4-FlashBackbone=DeepSeek-V4-Flash, Evaluation Protocol=mean@42026.07 | 44.74 |