| Benchmark | Model | Rank | Results |
|---|---|---|---|
| deep-research-agents-on-browsecomp-plus | DS-V4-Flash-Max + AgentIR-4B (stale-observation masking, K=5) | #2 | Accuracy: 84.3 |
| deep-research-agents-on-browsecomp-zh | DS-V4-Flash-Max + Serper API (stale-observation masking, K=5) | #2 | Accuracy: 73.4 |