BrowseComp-V3 - Process Score: leaderboard
Metric: Process score (%): mean share of each question's expert-annotated critical sub-goals the run achieves on 300 multimodal multi-hop browsing questions (Science 50, Technology 50, Society 75, Culture 75, Life 50) whose evidence is split across text and images on public web pages; OmniSeeker, the paper's browsing agent with TextSearch (Serper, top 5), WebVisit (Jina), ImageSearch, ImageCrop and ReverseImageSearch tools, up to 20 rounds per question, pass@1; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed 1.8 | 58.44 | #136 |
| 2 | GPT-5.2 | 57.7 | #105 |
| 3 | Claude Sonnet 4.5 | 54.17 | #138 |
| 4 | Gemini 3 Flash (Preview) | 47.37 | #78 |
| 5 | O4 Mini | 44.66 | #172 |
| 6 | MiMo-V2-Flash | 31.33 | #359 |
| 7 | Qwen 3 VL 235B A22B Instruct | 26.68 | #264 |
| 8 | GPT-4o | 24.15 | #333 |
| 9 | Qwen 3 VL 8B Instruct | 13.4 | #401 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=browsecomp-v3-process-score · How It Works · Data refreshed daily, snapshot 2026-10-11.