Meta Muse Wonder Scorecard - OSWorld V2.1 (strict binary completion): leaderboard
OSWorld V2.1: 108 long-horizon real-world workflows on a full Ubuntu desktop, controlled through screenshots, clicks and typing, run in Meta's common internal framework with the official task environments and graders. Share of tasks fully completed. Meta ran this for its October 12, 2026 Muse Wonder release scorecard, with every model at max reasoning effort; competitor runs are Meta's best-effort internal runs. Metric: Strict task completion (%). Higher is better. Source: https://research.meta.ai/blog/muse-wonder
Metric: Strict task completion (%). Source: research.meta.ai. Saturation forecast: Around 2029. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.1 (Max) | 43.1 | #9 (Claude Fable 5.1) |
| 2 | Muse Wonder Full (Max) | 39.4 | #10 (Muse Wonder Full) |
| 3 | GPT-6 Astra (Max) | 34.3 | #6 (GPT-6 Astra) |
| 4 | Muse Wonder (Max) | 34.3 | #14 (Muse Wonder) |
No result here: #4 Claude Opus 5.5, #7 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=meta-muse-wonder-scorecard-osworld-v2-1-strict-binary-completion · How It Works · Data refreshed daily, snapshot 2026-10-18.