BrowseComp-V3 - Society: leaderboard

Metric: Success rate (%): share of questions answered correctly on the 75 Society questions of BrowseComp-V3; 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 May 2027. 9 models tracked.

Top models

#ModelScoreOverall rank
1Seed 1.837.33#136
2GPT-5.233.33#105
3O4 Mini25.33#172
4Claude Sonnet 4.521.33#138
5Gemini 3 Flash (Preview)18.67#78
6Qwen 3 VL 235B A22B Instruct14.67#264
7GPT-4o10.67#333
8MiMo-V2-Flash10.67#359
9Qwen 3 VL 8B Instruct9.33#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-society · How It Works · Data refreshed daily, snapshot 2026-10-11.