# OSWorld 2.1 leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/agentic-os-world21

OSWorld 2.1 (all 108 tasks). Every model the catalog carries a published OSWorld 2.1 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Interactive computer-use evaluation; partial score |
| Tasks | 108 long-horizon computer-use workflows |
| Difficulty | Long-horizon professional workflows |
| Published by | [OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1)](https://github.com/xlang-ai/OSWorld-V2/releases) |

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.

## OSWorld 2.1 ranking

12 models with a published OSWorld 2.1 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Interactive computer-use evaluation; partial score | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 81.8 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 80.7 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Sonnet 5.5](https://modelscale.dev/models/claude-sonnet-5-5) | Anthropic | 80.1 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 79.6 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Hy4](https://modelscale.dev/models/hy4) | Tencent | 78.9 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Muse Wonder Full](https://modelscale.dev/models/muse-wonder-full) | Meta | 78.4 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 75.8 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | 74.0 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Muse Wonder](https://modelscale.dev/models/muse-wonder) | Meta | 72.6 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Muse Ember](https://modelscale.dev/models/muse-ember) | Meta | 69.5 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Hy4 flash](https://modelscale.dev/models/hy4-flash) | Tencent | 68.1 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Claude Sonnet 5](https://modelscale.dev/models/claude-sonnet-5) | Anthropic | 57.0 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
