OpenComputer: leaderboard
We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specific state verifiers that expose structured inspection endpoints over real applications, (2) a self-evolving verification layer that improves verifier reliability using execution-grounded feedback, (3) a task-generation pip
Metric: Success Rate (self-reported). Source: benchmarklist.com. Saturation forecast: Around July 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 68.3 | #79 |
| 2 | Claude Sonnet 4.6 | 64.4 | #90 |
| 3 | Kimi K2.6 | 58.8 | #104 |
| 4 | Qwen 3.5 27B | 32.3 | #187 |
| 5 | Gemini 3 Flash | 16.4 | #99 |
| 6 | Qwen 3.5 9B | 7.8 | #379 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=opencomputer · How It Works · Data refreshed daily, snapshot 2026-10-20.