OSWorld
Computer-use tasks
2.0agents and tool useactive
Score in %
Definition
- Version
- 2.0
- Category
- agents and tool use
- Maintainer
- XLANG Lab (HKU)
- Status
- active
- Home page
- not in the notes
Sources
- Anthropic releases Claude Opus 5.5 with Fable 5.1-level performance at lower cost - AI News vpsranking.com https://vpsranking.com/news/ai/ai-2026-09-22-anthropic-claude-opus-5-5/
- OpenAI Launches GPT-6 Astra, Pricing, Benchmarks and Who Gets It First pasqualepillitteri.it https://pasqualepillitteri.it/en/news/14246/openai-launches-gpt-6-astra-pricing-benchmarks
- OSWorld-Verified Leaderboard & Scores , October 2026 benchlm.ai https://www.benchlm.ai/benchmarks/osworld-verified
Scores at a Glance
Score in %
Higher is better for this unit.
1
Claude Opus 5.5AnthropicpartialClaude Fable 5.1Anthropic
GPT-6 AstraOpenAI
Claude Opus 5.5Anthropicpartial81.8 %
vendor-reported2Claude Fable 5.1Anthropic80.7 %
vendor-reported3GPT-6 AstraOpenAI72.6 %
vendor-reported0255075100
Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.
Scores
| Model | Score | Who ran it | Setting | View or population | Date | Source |
|---|---|---|---|---|---|---|
| Claude Opus 5.5 | 81.8 % | vendor-reported | partial | – | Sep 2026 | vpsranking.com |
| Claude Fable 5.1 | 80.7 % | vendor-reported | – | – | Sep 2026 | vpsranking.com |
| GPT-6 Astra | 72.6 % | vendor-reported | – | – | – | pasqualepillitteri.it |
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "OSWorld", https://aurion.semai.id/benchmarks/osworld-2-0/, records of October 2026.