Skip to main content
Evaluation sources/BrowseComp
ObservingKnowledge & language

BrowseComp

OpenAI · Public model evaluation results from BrowseComp.

Official evaluation
Source description

This source measures concrete delivery performance in Knowledge & language; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

GPT-5.6 Sol90.490.42026-07-09
GPT-5.5 Pro90.190.12026-04-23
GPT-5.4 Pro89.389.32026-04-23
GPT-5.6 Terra87.587.52026-07-09
Claude Sonnet 584.784.72026-06-30
GPT-5.584.484.42026-04-23
MiniMax-M383.5283.52026-06-01
GPT-5.6 Luna83.383.32026-07-09
GPT-5.482.782.72026-04-23
LongCat-2.079.979.92026-06-30
Step 3.7 Flash75.875.82026-05-29
Nemotron 3 Ultra 550B A55B44.444.42026-06-04

Frequently asked questions