Deep Research on BrowseComp-zh (Score)
81.3BrowseComp-zh ScoreSeed1.8
Evaluation Results
| Method | Links | |
|---|---|---|
| Seed1.8Context Management Technique=false2026.02 | 81.3 | |
| LongCat-Flash-ThinkingSize=560B-A27B, Context Management Technique=true2026.02 | 77.7 | |
| GPT-5.2-Thinking-xhighContext Management Technique=false2026.02 | 76.1 | |
| LongCat-Flash-ThinkingSize=560B-A27B, Context Management Technique=false2026.02 | 69 | |
| GLM-4.7Size=355B-A32B, Context Management Technique=true2026.02 | 67.5 | |
| DeepSeek-V3.2Size=671B-A37B, Context Management Technique=true2026.02 | 65 | |
| GPT-5-Thinking-highContext Management Technique=false2026.02 | 63 | |
| REDSearcherSize=30B-A3B, Context Management Technique=true2026.02 | 58.2 | |
| OpenAI-o3Context Management Technique=false2026.02 | 58.1 | |
| Gemini-3-ProContext Management Technique=false2026.02 | 51.6 | |
| REDSearcherSize=30B-A3B, Context Management Technique=false2026.02 | 49.8 | |
| Tongyi DeepResearch-30BSize=30B-A3B, Context Management Technique=false2026.02 | 46.7 | |
| WebResearcher-30BSize=30B-A3B, Context Management Technique=false2026.02 | 45.2 | |
| WebSailorV2-30BSize=30B-A3B, Context Management Technique=false2026.02 | 44.1 | |
| Claude-4.5-sonnetContext Management Technique=false2026.02 | 42.4 | |
| Gemini-2.5-pro-DRContext Management Technique=false2026.02 | 27.3 |