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 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
BrowseComp Long Context 256k leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 89.8% | 100.0% | 2 | C | |
| 2 | OP | 88.8% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
BrowseComp Long Context 256k highlights
The top published results on this benchmark's own scale.
What is BrowseComp Long Context 256k?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level 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
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.