Skip to main content
Benchmark Registry
Models
Benchmarks
Organizations
Compare
Search the registry
Search
OSWorld
Benchmark
OSWorld
Evaluated by
XLang Lab
Release date
July 28, 2025
Version
OSWorld Verified
Metric
OSWorld-Verified success rate
Search models
Search
Showing the selected evaluation.
Show all results
Results
1 result
Rows per page
50
100
500
Apply
Latest
History
All providers
Anthropic
OSWorld Verified results
Provider
Model
Score
Source
Registry No.
Anthropic
Claude Fable 5
85.0%
Source
for Claude Fable 5 on OSWorld Verified
(opens in a new tab)
20012
Previous
Page
1
of
1
Next