Hy-BrowseComp-Pro2 (Internal): leaderboard
Tencent’s internal Hy-BrowseComp-Pro2 agentic-search evaluation, listed in the HY4 preview benchmark appendix and noted as distinct from public BrowseComp benchmarks. The evaluated model uses text input. The pinned metric is the reported score. Source: BenchmarkList’s attributed result table.
Metric: Reported Score. Source: benchmarklist.com. Saturation forecast: Around November 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3 | 58.1 | #35 |
| 2 | GPT-5.6 Sol | 56.4 | #22 |
| 3 | GLM-5.3 | 48.4 | #44 |
| 4 | DeepSeek V4 Pro (0813) | 46.5 | #58 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=hy-browsecomp-pro2-internal · How It Works · Data refreshed daily, snapshot 2026-11-05.