Long-horizon research task on BrowseComp-ZH
82.4ScoreSeed-2.0-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Seed-2.0-ProSize=-, Context management=true2026.06 | 82.4 | |
| LongCat-Flash-Thinking-2601Size=560B-A27B, Context management=true2026.06 | 77.7 | |
| GPT-5.2-ThinkingSize=-, Context management=false2026.06 | 76.1 | |
| SearchSwarmSize=30B-A3B, Context management=true2026.06 | 73.3 | |
| GLM-5.0Size=744B-A40B, Context management=true2026.06 | 72.7 | |
| MiroThinker-1.7-miniSize=30B-A3B, Context management=true2026.06 | 72.3 | |
| Step-3.5-FlashSize=196B-A11B, Context management=false2026.06 | 66.9 | |
| Gemini-3.0-ProSize=-, Context management=false2026.06 | 66.8 | |
| MiroThinker-1.5-miniSize=30B-A3B, Context management=true2026.06 | 66.8 | |
| GLM-4.7Size=355B-A32B, Context management=true2026.06 | 66.6 | |
| GPT-5Size=-, Context management=false2026.06 | 65 | |
| DeepSeek V3.2Size=671B-A37B, Context management=true2026.06 | 65 | |
| LongSeekerSize=30B-A3B, Context management=true2026.06 | 62.5 | |
| Claude-4.5-OpusSize=-, Context management=false2026.06 | 62.4 | |
| RedSearcherSize=30B-A3B, Context management=true2026.06 | 58.2 | |
| Tongyi DeepResearchSize=30B-A3B, Context management=false2026.06 | 46.7 | |
| Tongyi DR SwarmSize=30B-A3B, Context management=false2026.06 | 46.7 | |
| Claude-4.5-SonnetSize=-, Context management=false2026.06 | 42.4 |