OSWorld
The original 369-task computer-use benchmark.
Agent Index weight
4%
in the Computer use pillar
Models tested
9
from the benchmark’s leaderboard and reports
Results
| # | Model | Score | Normalised | Harness | Cost/task | Date |
|---|---|---|---|---|---|---|
| 1 | Claude Sonnet 4.6 Supported Anthropic | 72.1% | claude-sonnet-4-6 (100 steps) | — | — | |
| 2 | Claude Opus 4.5 (latest) Supported Anthropic | 66.3% | Claude Opus 4.5 | — | Nov 25, 2025 | |
| 3 | Kimi K2.5 Supported Moonshot AI | 63.3% | Kimi-K2.5 | — | Feb 3, 2026 | |
| 4 | Claude Sonnet 4.5 (latest) Supported Anthropic | 62.9% | claude-sonnet-4-5-20250929 (100 steps) | — | Oct 30, 2025 | |
| 5 | Claude Sonnet 4 Supported Anthropic | 43.9% | claude-4-sonnet-20250514 (50 steps) | — | Jul 27, 2025 | |
| 6 | Claude 3.7 Sonnet Supported Anthropic | 35.8% | claude-3-7-sonnet-20250219 (50 steps) | — | Jul 27, 2025 | |
| 7 | computer-use-preview-2025-03-11 Unknown | 31.3% | computer-use-preview (50 steps) | — | Jul 27, 2025 | |
| 8 | o3 Supported OpenAI | 23.0% | o3 (100 steps) | — | Jul 27, 2025 | |
| 9 | Qwen2.5-72B Estimated Alibaba (Qwen) | 5.0% | qwen2.5-vl-72b-instruct (100 steps) | — | Jul 27, 2025 |
For models without a OSWorld result, the index estimates one from Epoch’s Capabilities Index using a logistic fit on 8 models (residual SD 0.59 on the logit scale). Estimates are labelled and widen the model’s range.