OSWorld-MCP — leaderboard
MCP tool-invocation benchmark for computer-use agents performing OSWorld-style desktop tasks.
Metric: Accuracy (%). Source: osworld-mcp.github.io. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 11 |
| 2 | Kimi K2.5 | 8 |
Interactive version: theaggregate.ai/benchmark?slug=osworld-mcp · How the rankings work · Data refreshed daily, snapshot 2026-07-22.