BrowseComp: leaderboard
BrowseComp is a text-only benchmark for autonomous agents on multi-step web tasks involving planning, state tracking, tool use, and recovery. The evaluated model is a browsing agent, and the pinned metric, Score (%), measures success on the benchmark tasks. Source: BenchmarkList’s attributed result table.
Metric: Score (%). Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3.1 Pro (Max) | 92.1 | #17 (Kimi K3.1 Pro) |
| 2 | GPT-6 Astra (Max) | 91.5 | #6 (GPT-6 Astra) |
| 3 | Claude Opus 5.5 (Max) | 90.8 | #3 (Claude Opus 5.5) |
No result here: #7 GPT-6.1 Sol, #9 Gemini 4 Argon, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=browsecomp · How It Works · Data refreshed daily, snapshot 2026-11-05.