LLM Stats (OSWorld 2.0): leaderboard
llm-stats.com’s mirror of OSWorld 2.0, the computer-use agent benchmark on real desktop applications. Its roster is currently disjoint from the first-party OSWorld 2.0 board — newer models only — and its scale matches the partial-credit column rather than the binary one.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around January 2027. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 81.8 | #3 |
| 2 | Claude Fable 5.1 | 77.9 | #9 |
| 3 | GPT-6 Astra | 72.6 | #6 |
| 4 | GPT-6.1 Sol | 71.42 | #7 |
| 5 | Claude Opus 5 | 70.6 | #12 |
| 6 | Gemini 4 Argon | 69.2 | #8 |
| 7 | Muse Spark 1.3 | 66.9 | #24 |
| 8 | GPT-6 Sol | 64.4 | #14 |
| 9 | GPT-5.6 Sol | 62.6 | #19 |
| 10 | MiniMax-M3.1-Flash | 61.7 | #33 |
| 11 | Gemini 3.8 Flash | 59 | #21 |
| 12 | GPT-6 Luna | 52.7 | #56 |
| 13 | GPT-5.6 Terra | 50.2 | #41 |
| 14 | Gemini 3.7 Flash | 47.9 | #23 |
| 15 | GPT-5.6 Luna | 45.6 | #68 |
No result here: #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-osworld-2-0 · How It Works · Data refreshed daily, snapshot 2026-10-20.