Model
Computer Use Preview (2025-03-11)
Vendor N/A
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| OSWorld | 31.3 | score | computer-use-preview (50 steps) | Independent | medium | os-world.github.io |
| OSWorld | 30.5 | score | computer-use-preview (100 steps) | Independent | medium | os-world.github.io |
| OSWorld | 26.0 | score | computer-use-preview (15 steps) | Independent | medium | os-world.github.io |
Reproduced by the community
Loading community runs…