Subjective Search Question Answering on Internal Evaluation Subjective Q&A
190V4 Win CountDeepSeek-V4-Pro
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DeepSeek-V4-ProSubcategory=Subtotal (小计), #=6672026.04 | 190 | 74 | 403 | 28.5 | 11.1 | 60.4 | |
| DeepSeek-V3.2Subcategory=Subtotal (小计), #=6672026.04 | 190 | 74 | 403 | 28.5 | 11.1 | 60.4 | |
| DeepSeek-V4-ProSubcategory=Planning & Strategy (攻略计划), #=922026.04 | 32 | 11 | 49 | 34.8 | 12 | 53.3 | |
| DeepSeek-V3.2Subcategory=Planning & Strategy (攻略计划), #=922026.04 | 32 | 11 | 49 | 34.8 | 12 | 53.3 | |
| DeepSeek-V4-ProSubcategory=Opinion & Evaluation (评价看法), #=962026.04 | 30 | 8 | 58 | 31.2 | 8.3 | 60.4 | |
| DeepSeek-V3.2Subcategory=Opinion & Evaluation (评价看法), #=962026.04 | 30 | 8 | 58 | 31.2 | 8.3 | 60.4 | |
| DeepSeek-V4-ProSubcategory=Causal Analysis (原因分析), #=1002026.04 | 28 | 5 | 67 | 28 | 5 | 67 | |
| DeepSeek-V3.2Subcategory=Causal Analysis (原因分析), #=1002026.04 | 28 | 5 | 67 | 28 | 5 | 67 | |
| DeepSeek-V4-ProSubcategory=Comparison (对比), #=962026.04 | 28 | 20 | 48 | 29.2 | 20.8 | 50 | |
| DeepSeek-V3.2Subcategory=Comparison (对比), #=962026.04 | 28 | 20 | 48 | 29.2 | 20.8 | 50 | |
| DeepSeek-V4-ProSubcategory=Recommendation (推荐), #=952026.04 | 26 | 19 | 50 | 27.4 | 20 | 52.6 | |
| DeepSeek-V3.2Subcategory=Recommendation (推荐), #=952026.04 | 26 | 19 | 50 | 27.4 | 20 | 52.6 | |
| DeepSeek-V4-ProSubcategory=Advice Seeking (寻求建议), #=922026.04 | 23 | 8 | 61 | 25 | 8.7 | 66.3 | |
| DeepSeek-V3.2Subcategory=Advice Seeking (寻求建议), #=922026.04 | 23 | 8 | 61 | 25 | 8.7 | 66.3 | |
| DeepSeek-V4-ProSubcategory=Trend Analysis (趋势分析), #=962026.04 | 23 | 3 | 70 | 24 | 3.1 | 72.9 | |
| DeepSeek-V3.2Subcategory=Trend Analysis (趋势分析), #=962026.04 | 23 | 3 | 70 | 24 | 3.1 | 72.9 |