Benchmark
BrowseComp Long Context 128k Benchmark
What is 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…
- Modality
- text
- Evaluates
- reasoning, search
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 5
Source provenance
BrowseComp Long Context 128k results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-5 | OpenAI | 0.9 | 2025-08-07 | evidence |
| GPT-5.1 | OpenAI | 0.9 | 2025-11-13 | evidence |
| GPT-5.1 Instant | OpenAI | 0.9 | 2025-11-12 | evidence |
| GPT-5.1 Thinking | OpenAI | 0.9 | 2025-11-12 | evidence |
| GPT-5.2 | OpenAI | 0.92 | 2025-12-11 | 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.