reasoning benchmark
BrowseComp-zh Leaderboard
BrowseComp-zh is a reasoning benchmark for evaluating LLM agents on 289 multi-hop questions across 11 domains on the Chinese web.
Updated Sep 5, 2026
Models13
Model coverage13
MetricScore
EvidenceB
BrowseComp-zh Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score70.30% | Percentile100.00% | Participants13 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score69.90% | Percentile91.67% | Participants13 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score69.50% | Percentile83.33% | Participants13 | EvidenceC | Evaluated |
| Rank04 | ModelME | Score69.00% | Percentile75.00% | Participants13 | EvidenceC | Evaluated |
| Rank05 | ModelZA | Score66.60% | Percentile66.67% | Participants13 | EvidenceC | Evaluated |
| Rank06 | ModelDE | Score65.00% | Percentile58.33% | Participants13 | EvidenceC | Evaluated |
| Rank07 | ModelDE | Score65.00% | Percentile50.00% | Participants13 | EvidenceC | Evaluated |
| Rank08 | ModelMA | Score62.30% | Percentile41.67% | Participants13 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score62.10% | Percentile33.33% | Participants13 | EvidenceC | Evaluated |
| Rank10 | ModelDE | Score49.20% | Percentile25.00% | Participants13 | EvidenceC | Evaluated |
| Rank11 | ModelMI | Score48.50% | Percentile16.67% | Participants13 | EvidenceC | Evaluated |
| Rank12 | ModelDE | Score47.90% | Percentile8.33% | Participants13 | EvidenceC | Evaluated |
| Rank13 | ModelDE | Score35.70% | Percentile0.00% | Participants13 | EvidenceC | Evaluated |
BrowseComp-zh Highlights
The leading models and scores on this benchmark.
BrowseComp-zh Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for BrowseComp-zh
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is BrowseComp-zh?
What BrowseComp-zh measures and how its scores work.
BrowseComp-zh is a benchmark consisting of 289 multi-hop questions spanning 11 domains, including Film & TV, Technology, Medicine, and History.
It measures LLM agent performance on questions requiring reasoning and information reconciliation on the Chinese web, reported as a Score ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BrowseComp-zh
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BrowseComp-zh.
Which model scores highest on BrowseComp-zh?
Qwen3.5-397B-A17B is currently ranked first with 70.30%.
What are the top three models on BrowseComp-zh?
The current leaders are Qwen3.5-397B-A17B (70.30%), Qwen3.5-122B-A10B (69.90%), and Qwen3.5-35B-A3B (69.50%).
Which BrowseComp-zh model has the lowest official input price?
Qwen3.5-35B-A3B has the lowest matched official input price at $0.25 input / $2.0 output per 1M tokens.
Which models are fastest among BrowseComp-zh results?
The fastest matched records are DeepSeek-V3.2 (97.00 tok/s via DeepInfra), DeepSeek-V3.2-Exp (97.00 tok/s via DeepInfra), and MiniMax M2 (70.00 tok/s via MiniMax).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.