Deep Search on xBench DeepSearch (05)
75ScoreTongyi-DeepResearch-30B
Evaluation Results
| Method | Links | |
|---|---|---|
| Tongyi-DeepResearch-30BCategory=Research Agent2026.02 | 75 | |
| Nanbeige4.1-3BCategory=Ours2026.02 | 75 | |
| Minimax-M2-230BCategory=Large Foundation Model2026.02 | 72 | |
| DeepSeek-V3.2-671BCategory=Large Foundation Model2026.02 | 71 | |
| AgentCPM-Explore-4BCategory=Research Agent2026.02 | 70 | |
| GLM-4.6-357BCategory=Large Foundation Model2026.02 | 70 | |
| MiroThinker-v1.0-8BCategory=Research Agent2026.02 | 60.6 | |
| Qwen3-32BCategory=Small Foundation Model2026.02 | 39 | |
| Qwen3-4B-2507Category=Small Foundation Model2026.02 | 34 | |
| Qwen3-14BCategory=Small Foundation Model2026.02 | 34 | |
| Nanbeige4-3B-2511Category=Baseline2026.02 | 33 | |
| Qwen3-8BCategory=Small Foundation Model2026.02 | 31 | |
| Qwen3-Next-80B-A3BCategory=Small Foundation Model2026.02 | 27 | |
| Qwen3-30B-A3B-2507Category=Small Foundation Model2026.02 | 25 |