China AI Hub China AI Hub

Benchmarks / BrowseComp

BrowseComp

Benchmark of browsing and retrieval ability: locating obscure information using web search and browsing.

BrowseComp
Image: AI-generated illustration (Seedream)

Benchmark of browsing and retrieval ability: locating obscure information using web search and browsing. The table below lists 3 recorded evaluations across 3 models: kimi-k3, kimi-k2.5, minimax-m3. All entries are labeled by source type (vendor_reported) with links to the original publication. See the Limitations section for comparability caveats before citing any score.

Benchmark methodology

Methodology of BrowseComp
Task type Browsing agent benchmark (locate hard-to-find, entangled information on the internet)
Dataset size 1,266 problems
Evaluation method Short-answer questions with a single correct answer; graders verify the exact answer (encrypted set)
Scoring Accuracy (% correct)
Last verified: · Data status: Current · Next review:

Results

Results for BrowseComp
Model Model version Score Metric Date Source type Source
kimi-k3 91.2 (90.4 with full 1M context, no compaction) accuracy 2026-07 vendor_reported link
kimi-k2.5 60.6 (74.9 with context management; 78.4 Agent Swarm) accuracy vendor_reported link
minimax-m3 83.5 accuracy 2026-06-01 vendor_reported link

Limitations

All scores are vendor-reported and not independently verified. Evaluation setups (context management, agent scaffolding) differ between vendors.

Vendor-reported scores are labeled as such. Scores from incompatible benchmark versions are never mixed without explanation.

Sources

What does BrowseComp measure?

Benchmark of browsing and retrieval ability: locating obscure information using web search and browsing.

Which Chinese AI models have published BrowseComp results?

kimi-k3, kimi-k2.5, minimax-m3.

Are BrowseComp scores independently verified?

Results on this page are labeled by source type (vendor_reported). Vendor-reported scores are labeled as such, and scores from incompatible benchmark versions are never mixed.

Where does China AI Hub get its BrowseComp data?

From 3 sources, last verified 2026-09-20.