← Benchmarks
OSWorld
OSWorld: The first-of-its-kind scalable, real computer environment for multimodal agents, supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS with 369 computer tasks involving real web and desktop applications, OS file I/O, and multi-application workflows
id osworld · max 1 · 21 models reported
| # | Model | Score |
|---|---|---|
| 1 | Seed 2.1 Pro ByteDance | 0.79 |
| 2 | Seed 2.1 Turbo ByteDance | 0.76 |
| 3 | Claude Opus 4.6 Anthropic | 0.73 |
| 4 | Claude Sonnet 4.6 Anthropic | 0.72 |