Skip to content
THE AI RACE
Leaderboard
Compare
Benchmarks
Methodology
Changelog
Movers
Time Machine
⌘K
☰
THE AI RACE
Leaderboard
Compare
Benchmarks
Methodology
Changelog
Movers
Time Machine
⌘K
☰
THE AI RACE
Leaderboard
Compare
Benchmarks
Methodology
Changelog
Movers
Time Machine
⌘K
☰
← Back to Benchmarks
WebArena
Web interaction tasks in realistic simulated environments
Agents & Tools
Unit: %
Max: 100
Source →
Rankings (6 organizations)
1
Anthropic
48%
2
OpenAI
45%
3
Google DeepMind
42%
4
DeepSeek
32%
5
Meta AI
28%
6
xAI
25%
Other Benchmarks in Agents & Tools
TAU2-bench
Terminal-Bench
All Categories
Language & Knowledge
Coding
Reasoning & Math
Image Generation
Video Generation
Multimodal
Agents & Tools