# OSWorld 2.1 (all 108 tasks) (OSWorld 2.1)

> OSWorld 2.1 is the current release of OSWorld 2.0: the same 108 long-horizon computer-use workflows with the maintainers' later fixes to task files, assets, mocked websites, and evaluators. This page stores partial scores on the full task set.

Canonical page: https://benchlm.ai/benchmarks/osworld-2-1

- Category: [Agentic](/agentic)
- Last updated: October 27, 2026

## About OSWorld 2.1

- Year: 2026
- Tasks: 108 long-horizon computer-use workflows
- Format: Interactive computer-use evaluation; partial score
- Difficulty: Long-horizon professional workflows
- Paper: [OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1)](https://github.com/xlang-ai/OSWorld-V2/releases)

The osworld-v2.1 release pins task files, gated assets, mocked websites, and the Ubuntu VM image for reproducible runs and adds an offline task subset. Labs report a partial score (mean per-task checkpoint credit) and a strict pass rate; we store the partial score, the metric every source here publishes, and keep strict pass rates in the source notes. Runs use each lab's own harness, so treat gaps of a few points as unresolved. Results on the earlier OSWorld 2.0 releases stay on the OSWorld 2.0 page, and the 82-task offline subset has its own page.

OSWorld 2.1 is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (9 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 81.8% |
| 2 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | 80.7% |
| 3 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | Anthropic | 80.1% |
| 4 | [Kimi K3.1 Pro](/models/kimi-3-1-pro) | Moonshot AI | 79.6% |
| 5 | [Muse Wonder Full](/models/muse-wonder-full) | Meta | 78.4% |
| 6 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | 75.8% |
| 7 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | 74.0% |
| 8 | [Muse Wonder](/models/muse-wonder) | Meta | 72.6% |
| 9 | [Claude Sonnet 5](/models/claude-sonnet-5) | Anthropic | 57.0% |

## FAQ

### How is OSWorld 2.1 different from OSWorld 2.0?

OSWorld 2.1 is the maintainers' current release of OSWorld 2.0. It keeps the 108 workflows but fixes task evaluators, assets, and mocked websites, so its scores are not like-for-like with results on the June or August 2026 OSWorld 2.0 releases. Those results stay on the OSWorld 2.0 page.

### Why is the offline subset on a separate page?

The offline subset runs 82 of the 108 tasks with no internet access in the agent's virtual machine. Anthropic reports Claude Sonnet 5.5 at 80.1% on all 108 tasks and 83.9% on the offline subset, so mixing the two would distort the comparison.

## Compare Top Models on OSWorld 2.1

- [Claude Opus 5.5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-opus-5-5)
- [Claude Fable 5.1 vs Claude Sonnet 5.5](/compare/claude-fable-5-1-vs-claude-sonnet-5-5)
- [Claude Sonnet 5.5 vs Kimi K3.1 Pro](/compare/claude-sonnet-5-5-vs-kimi-3-1-pro)
- [Kimi K3.1 Pro vs Muse Wonder Full](/compare/kimi-3-1-pro-vs-muse-wonder-full)