Deep Search on SEAL 0
41.44ScoreNanbeige4.1-3B
Evaluation Results
| Method | Links | |
|---|---|---|
| Nanbeige4.1-3BCategory=Ours2026.02 | 41.44 | |
| MiroThinker-v1.0-8BCategory=Research Agent2026.02 | 40.4 | |
| AgentCPM-Explore-4BCategory=Research Agent2026.02 | 40 | |
| DeepSeek-V3.2-671BCategory=Large Foundation Model2026.02 | 38.5 | |
| Qwen3-Next-80B-A3BCategory=Small Foundation Model2026.02 | 18.18 | |
| Qwen3-4B-2507Category=Small Foundation Model2026.02 | 15.74 | |
| Qwen3-14BCategory=Small Foundation Model2026.02 | 12.64 | |
| Nanbeige4-3B-2511Category=Baseline2026.02 | 12.61 | |
| Qwen3-30B-A3B-2507Category=Small Foundation Model2026.02 | 9.24 | |
| Qwen3-32BCategory=Small Foundation Model2026.02 | 8.15 | |
| Qwen3-8BCategory=Small Foundation Model2026.02 | 6.34 |