BrowseComp

general
text
About

BrowseComp benchmark

Evaluation Stats
Total Models3
Organizations1
Verified Results0
Self-Reported3
Benchmark Details
Max Score1
Language
en
Sub-benchmarks2
Performance Overview
Score distribution and top performers

Score Distribution

3 models
Top Score
54.9%
Average Score
52.0%
High Performers (80%+)
0

Top Organizations

#1OpenAI
3 models
52.0%
Leaderboard
Top 3 models ranked by performance
54.9%
Raw: 0.549
Self-reported
51.5%
Raw: 0.515
Self-reported
49.7%
Raw: 0.497
Self-reported