Web-based Agent QA on WebWalkerQA
73.53Pass@1Agent KB
Evaluation Results
| Method | Links | |
|---|---|---|
| Agent KBModel Family=GPT-4.1, pass@k protocol=pass@32026.02 | 73.53 | |
| TodoEvolve + SmolagentsModel Family=GPT-5-Mini, pass@k protocol=pass@12026.02 | 73.53 | |
| Flash-SearcherModel Family=GPT-5-mini, pass@k protocol=pass@12026.02 | 71.18 | |
| TodoEvolve + SmolagentsModel Family=DeepSeek V3.2, pass@k protocol=pass@12026.02 | 70.59 | |
| Flash-SearcherModel Family=DeepSeek V3.2, pass@k protocol=pass@12026.02 | 69.41 | |
| Agent KBModel Family=GPT-4.1, pass@k protocol=pass@22026.02 | 68.82 | |
| TodoEvolve + SmolagentsModel Family=Kimi K2, pass@k protocol=pass@12026.02 | 64.71 | |
| Cognitive Kernel-ProModel Family=Claude-3.7 etc., pass@k protocol=pass@12026.02 | 60.64 | |
| Agent KBModel Family=GPT-4.1, pass@k protocol=pass@12026.02 | 60.59 | |
| SmolagentsModel Family=GPT-5-mini, pass@k protocol=pass@12026.02 | 58.82 | |
| OAgentsModel Family=Claude-3.7 etc., pass@k protocol=pass@12026.02 | 58.23 | |
| OWL WorkforceModel Family=GPT-4o+o3-mini, pass@k protocol=pass@32026.02 | 57.64 | |
| Flash-SearcherModel Family=Kimi K2, pass@k protocol=pass@12026.02 | 52.35 | |
| WebAggregatorBackbone=Qwen2.5-32B2025.10 | 45.7 | |
| WebAggregatorBackbone=Qwen2.5-7B2025.10 | 44.7 | |
| WebAggregatorBackbone=Qwen3-32B2025.10 | 43.5 | |
| WebAggregatorBackbone=Qwen3-8B2025.10 | 41.2 | |
| GPT-4.12025.10 | 39.9 | |
| WebDancerBackbone=Qwen2.5-32B2025.10 | 38.4 | |
| WebDancerBackbone=Qwen2.5-7B2025.10 | 36 |