reasoning benchmark
BrowseComp Long Context 128k
A challenging benchmark for evaluating web browsing agents' ability to persistently navigate the internet and find hard-to-locate, entangled information. Comprises 1,266 questions requiring strategic reasoning, creative search, and interpretation of retrieved content, with short and easily verifiable answers.
Updated Aug 11, 2026
Models5
Model coverage5
MetricScore
EvidenceB
BrowseComp Long Context 128k Ranking
Higher score ranks better on this benchmark.
| 1 | OP | 92.0% | 100.0% | 5 | C | |
| 2 | OP | 90.0% | 75.0% | 5 | C | |
| 3 | OP | 90.0% | 50.0% | 5 | C | |
| 4 | OP | 90.0% | 25.0% | 5 | C | |
| 5 | OP | 90.0% | 0.0% | 5 | C |
BrowseComp Long Context 128k Score Distribution
A closer view of the leading scores on this benchmark.
BrowseComp Long Context 128k Highlights
The leading models and scores on this benchmark.
What is BrowseComp Long Context 128k?
What BrowseComp Long Context 128k measures and how its scores work.
A challenging benchmark for evaluating web browsing agents' ability to persistently navigate the internet and find hard-to-locate, entangled information. Comprises 1,266 questions requiring strategic reasoning, creative search, and interpretation of retrieved content, with short and easily verifiable answers.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BrowseComp Long Context 128k
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- browsecomp-long-128k|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BrowseComp Long Context 128k.
Which model scores highest on BrowseComp Long Context 128k?
GPT-5.2 is currently ranked first with 92.0%.
What does BrowseComp Long Context 128k measure?
A challenging benchmark for evaluating web browsing agents' ability to persistently navigate the internet and find hard-to-locate, entangled information. Comprises 1,266 questions requiring strategic reasoning, creative search, and interpretation of retrieved content, with short and easily verifiable answers.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
5 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.