Benchmark Almanac

computer-use-preview-2025-03-11

computer-use-preview-2025-03-11.

Released March 11th, 2025 Compare with others
3
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Mar 2025

computer-use-preview-2025-03-11

No Epoch Capabilities Index score yet
  • OSWorld 31.3% #6 /8
  • GameWorld 35.8% #18 /22
  • OSWorld-Verified 31.3% #27 /33

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Agents and tools

BenchmarkScoreRankSource
OSWorld 31.3% #6 of 8 OS World Website, via Epoch AI
OSWorld-Verified 31.3% #27 of 33 Official leaderboard
GameWorld 35.8% #18 of 22 Official leaderboard