Deep Search on BrowseComp EN
67.6ScoreSeed1.8
Evaluation Results
| Method | Links | |
|---|---|---|
| Seed1.8Size=-, Category=Commercial Closed-source Models2026.04 | 67.6 | |
| GPT-5.2 (xhigh)Size=-, Category=Commercial Closed-source Models2026.04 | 65.8 | |
| GLM-5Size=744B-A40B, Category=Open-source Large-scale Models (w/o ctm)2026.04 | 62 | |
| Kimi-K2.5Size=1T-A32B, Category=Open-source Large-scale Models (w/o ctm)2026.04 | 60.6 | |
| Gemini-3-ProSize=-, Category=Commercial Closed-source Models2026.04 | 59.2 | |
| Claude Opus 4.5Size=-, Category=Commercial Closed-source Models2026.04 | 57.8 | |
| GLM-4.7Size=355B-A32B, Category=Open-source Large-scale Models (w/o ctm)2026.04 | 52 | |
| DeepSeek-V3.2Size=671B-A37B, Category=Open-source Large-scale Models (w/o ctm)2026.04 | 51.4 | |
| QuarkMedSearchSize=30B-A3B, Category=Ours2026.04 | 47.03 | |
| SMTL-100Size=30B-A3B, Category=Open-source Medium-scale Models (w/o ctm)2026.04 | 43.6 | |
| Tongyi DeepResearchSize=30B-A3B, Category=Open-source Medium-scale Models (w/o ctm)2026.04 | 43.4 | |
| Base (Tongyi DeepResearch)†Size=30B-A3B, Category=Ours, Evaluation Environment=Unified2026.04 | 42.67 | |
| REDSearcherSize=30B-A3B, Category=Open-source Medium-scale Models (w/o ctm)2026.04 | 42.1 | |
| WebResearcherSize=30B-A3B, Category=Open-source Medium-scale Models (w/o ctm)2026.04 | 37.3 | |
| WebSailorV2Size=30B-A3B, Category=Open-source Medium-scale Models (w/o ctm)2026.04 | 35.3 |