BrowseComp Long Context - 256K
General QA · 2025-08-07
BrowseComp Long Context gives the model a BrowseComp-style question together with a long list of relevant search results and asks it to answer from that context alone, without browsing. This row is the 256K-input bin (OpenAI describes inputs of 128K-256K tokens). Scores are answer accuracy. Higher is better.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.2 | 89.8 |
| GPT-5.1 | 89.5 |
| GPT-5 | 88.8 |
| GPT-5 Mini | 86.0 |
| GPT-4.1 Mini | 81.6 |
| GPT-4.1 | 75.5 |
| GPT-5 Nano | 68.4 |
| GPT-4.1 Nano | 19.1 |