Benchmark · agentic
OSWorld 2.0
2026 long-horizon re-cut of OSWorld: 108 multi-app desktop workflows, median human task ~1.6h. Not on the same scale as OSWorld / OSWorld-Verified — file here only when the quote says 2.0.
| 日期 | 模型 | 得分 | 来源 |
|---|---|---|---|
| 2026-07-28 | Claude Opus 5 | 70.0% | Anthropic 发布 Claude Opus 5，作为 Fable 的高性价比替代方案 |