Benchmark
BrowseComp Benchmark
What is BrowseComp?
Live web. The result depends on what the internet contained on the day of the run. Benchmark Radar tracks 9 reported scores for BrowseComp, cited by 12 source…
- Released
- 2025-04-10
- Evaluates
- agent
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 9
Source provenance
- Original evidence https://openai.com/index/browsecomp/
BrowseComp links
BrowseComp results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| DeepSeek-V4-Flash | DeepSeek | 73.2 | 2026-06-25 | evidence |
| DeepSeek-V4-Pro | DeepSeek | 80.4 | 2026-04-22 | evidence |
| DeepSeek-V4-Pro | DeepSeek | 83.4 | 2026-04-22 | evidence |
| Gemini 3.1 Pro | 85.9 | 2026-02-19 | evidence | |
| GLM-5 | Z.ai | 62.0 | 2026-02-11 | evidence |
| GLM-5.1 | Z.ai | 68.0 | 2026-04-03 | evidence |
| Kimi K3 | Moonshot AI | 91.2 | 2026-06-13 | evidence |
| Qwen3.5-397B-A17B | Qwen | 78.6 | 2026-02-16 | evidence |
| Qwen3.5-397B-A17B | Qwen | 69.0 | 2026-02-16 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.
Which sources cite BrowseComp?
- GPT-5.6 (Sol, Terra, Luna) OpenAI, 2026-07-09
- GPT-5.6 OpenAI, 2026-06-26
- DeepSeek-V4 DeepSeek, 2026-06-25
- Kimi K3 Moonshot AI, 2026-06-13
- DeepSeek-V4-Pro DeepSeek, 2026-04-22
- GLM-5.1 Z.ai, 2026-04-03
- Gemini 3.1 Pro Google, 2026-02-19
- Qwen3.5-397B-A17B Qwen, 2026-02-16
- GLM-5 Z.ai, 2026-02-11
- GLM-5 Z.ai, 2026-02-11
- GPT-5 OpenAI, 2025-08-07
- o3 and o4-mini OpenAI, 2025-04-16