BrowseComp: A Benchmark for Browsing Agents.

Hard web-browsing QA benchmark with short factual answers that require persistent search over many online sources.

Best published scores.

16 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary

accuracy · higher is better

6 steps
of state of the art.

Each row below marks a model that broke the previous record on accuracy. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

1. Aug 8, 2025GLM-4.5Zhipu AI26.40
2. Dec 2, 2025DeepSeek-V3.2DeepSeek51.40
3. Feb 2, 2026Kimi-K2.5Moonshot.AI60.60
4. Feb 12, 2026MiniMax-M2.5MiniMaxAI76.30
5. Apr 20, 2026Kimi K2.683.20
6. Apr 24, 2026DeepSeek-V4-Pro MaxDeepSeek83.40

6 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

Neighbouring benchmarks.

Other Question Answering datasets on Codesota.

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

• 01A public checkpoint or API endpoint
• 02A reproduction script with frozen commit + seed
• 03Declared evaluation environment (Python, deps)
• 04One row per metric declared by this dataset
• 05A contact so we can follow up on discrepancies