reasoning benchmark
BrowseComp Long Context 256k
BrowseComp is a benchmark for measuring the ability of agents to browse the web, comprising 1,266 questions that require persistently navigating the internet in search of hard-to-find, entangled information. Despite the difficulty of the questions, BrowseComp is simple and easy-to-use, as predicted answers are short and easily verifiable against reference answers. The benchmark focuses on questions where answers are obscure, time-invariant, and well-supported by evidence scattered across the open web.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
BrowseComp Long Context 256k Ranking
Higher score ranks better on this benchmark.
| 1 | OP | 89.8% | 100.0% | 2 | C | |
| 2 | OP | 88.8% | 0.0% | 2 | C |
BrowseComp Long Context 256k Score Distribution
A closer view of the leading scores on this benchmark.
BrowseComp Long Context 256k Highlights
The leading models and scores on this benchmark.
What is BrowseComp Long Context 256k?
What BrowseComp Long Context 256k measures and how its scores work.
BrowseComp is a benchmark for measuring the ability of agents to browse the web, comprising 1,266 questions that require persistently navigating the internet in search of hard-to-find, entangled information. Despite the difficulty of the questions, BrowseComp is simple and easy-to-use, as predicted answers are short and easily verifiable against reference answers. The benchmark focuses on questions where answers are obscure, time-invariant, and well-supported by evidence scattered across the open web.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BrowseComp Long Context 256k
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- browsecomp-long-256k|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BrowseComp Long Context 256k.
Which model scores highest on BrowseComp Long Context 256k?
GPT-5.2 is currently ranked first with 89.8%.
What does BrowseComp Long Context 256k measure?
BrowseComp is a benchmark for measuring the ability of agents to browse the web, comprising 1,266 questions that require persistently navigating the internet in search of hard-to-find, entangled information. Despite the difficulty of the questions, BrowseComp is simple and easy-to-use, as predicted answers are short and easily verifiable against reference answers. The benchmark focuses on questions where answers are obscure, time-invariant, and well-supported by evidence scattered across the open web.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.