Objective Search Question Answering on Internal Evaluation Objective Q&A
269V4 WinsDeepSeek-V4-Pro
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DeepSeek-V4-ProSubcategory=TOTAL (总计), #=9562026.04 | 269 | 99 | 588 | 28.1 | 10.4 | 61.5 | |
| DeepSeek-V3.2Subcategory=TOTAL (总计), #=9562026.04 | 269 | 99 | 588 | 28.1 | 10.4 | 61.5 | |
| DeepSeek-V4-ProSubcategory=Subtotal (小计), #=2892026.04 | 79 | 25 | 185 | 27.3 | 8.7 | 64 | |
| DeepSeek-V3.2Subcategory=Subtotal (小计), #=2892026.04 | 79 | 25 | 185 | 27.3 | 8.7 | 64 | |
| DeepSeek-V4-ProSubcategory=Single-value Search (单值信息查找), #=952026.04 | 36 | 10 | 49 | 37.9 | 10.5 | 51.6 | |
| DeepSeek-V3.2Subcategory=Single-value Search (单值信息查找), #=952026.04 | 36 | 10 | 49 | 37.9 | 10.5 | 51.6 | |
| DeepSeek-V4-ProSubcategory=Entity Search (实体信息查找), #=992026.04 | 24 | 7 | 68 | 24.2 | 7.1 | 68.7 | |
| DeepSeek-V3.2Subcategory=Entity Search (实体信息查找), #=992026.04 | 24 | 7 | 68 | 24.2 | 7.1 | 68.7 | |
| DeepSeek-V4-ProSubcategory=Enumerative Search (枚举型信息查找), #=952026.04 | 19 | 8 | 68 | 20 | 8.4 | 71.6 | |
| DeepSeek-V3.2Subcategory=Enumerative Search (枚举型信息查找), #=952026.04 | 19 | 8 | 68 | 20 | 8.4 | 71.6 |