# OSWorld 2.0 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-world2

Every model the catalog carries a published OSWorld 2.0 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Interactive computer-use evaluation; binary completion and partial-score metrics |
| Tasks | 108 long-horizon computer-use workflows |
| Difficulty | Long-horizon professional workflows |
| Published by | [OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks](https://arxiv.org/abs/2606.29537) |

OSWorld 2.0 evaluates long-horizon computer-use tasks. Published results use different task releases, metrics, and run settings, so scores appear by comparable protocol and unmatched rows stay unranked.

## OSWorld 2.0 ranking

25 models with a published OSWorld 2.0 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; binary completion and partial-score metrics | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 79.6 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 72.6 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | 70.6 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 69.2 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Muse Spark 1.3](https://modelscale.dev/models/muse-spark-1-3) | Meta | 66.9 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-5.6 Sol](https://modelscale.dev/models/gpt-5-6-sol) | OpenAI | 62.6 | Observed 2026-11-21 · source benchlm:models |
| 7 | [MiniMax M3.1 Flash](https://modelscale.dev/models/minimax-m3-1-flash) | MiniMax | 61.7 | Observed 2026-11-21 · source benchlm:models |
| 8 | [GPT-6 Sol](https://modelscale.dev/models/gpt-6-sol) | OpenAI | 60.5 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 59.0 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-5.6 Terra](https://modelscale.dev/models/gpt-5-6-terra) | OpenAI | 50.2 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 48.7 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Gemini 3.7 Flash](https://modelscale.dev/models/gemini-3-7-flash) | Google | 47.9 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-5.6 Luna](https://modelscale.dev/models/gpt-5-6-luna) | OpenAI | 45.6 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 41.7 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | 20.6 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | 19.4 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Qwen3.8-Flash-Next](https://modelscale.dev/models/qwen3-8-flash-next) | Alibaba | 19.4 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Claude Opus 4.7](https://modelscale.dev/models/claude-opus-4-7) | Anthropic | 18.2 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Claude Opus 4.7 (Adaptive)](https://modelscale.dev/models/claude-opus-4-7-max) | Anthropic | 18.2 | Last good 2026-11-18 · source benchlm:models |
| 20 | [Muse Spark 1.1](https://modelscale.dev/models/muse-spark-1-1) | Meta | 14.2 | Observed 2026-11-21 · source benchlm:models |
| 21 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | 13.0 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Claude Sonnet 4.6](https://modelscale.dev/models/claude-sonnet-4-6) | Anthropic | 8.3 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | 4.6 | Observed 2026-11-21 · source benchlm:models |
| 23 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | 4.6 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Qwen3.7 Plus](https://modelscale.dev/models/qwen3-7-plus) | Alibaba | 2.8 | 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.
