BlogLLM Benchmark Scores as Published, Side by Side
BrowseComp Long Context: Results as Published
Every result the catalog holds for BrowseComp Long Context: 3 models from 1 developer, read from 2 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Long ContextMaintainer OpenAIData version 2026103001, as of 2026-10-30
BrowseComp Long Context takes questions from BrowseComp, the OpenAI browsing benchmark of hard-to-find facts, and places the web content needed to answer them inside the prompt instead of behind a search tool, at a stated context length (128k or 256k tokens). It measures whether a model can find and combine the relevant pieces of a long context rather than whether it can search.
Not checked against a maintainer's page.
BrowseComp Long Context 128k
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.2OpenAI, released 2025-12-11 | 92% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: xhigh; Context: 128k |
| GPT-5.1OpenAI, released 2025-11-12 | 90% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15; printed on 1 more page | Effort: high; Context: 128k |
| GPT-5OpenAI, released 2025-08-07 | 90% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15 | Effort: high; Context: 128k |
BrowseComp Long Context 256k
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.2OpenAI, released 2025-12-11 | 89.8% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: xhigh; Context: 256k |
| GPT-5.1OpenAI, released 2025-11-12 | 89.5% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Context: 256k |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.