New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
OSWorld-Verified benchmark
AI model leaderboard for the OSWorld-Verified benchmark. Compare how large language models score on OSWorld-Verified, see the full ranking, and understand what this AI benchmark measures. Claude Fable 5 currently leads with 85%. Verified split of OSWorld — real computer-use GUI agent tasks.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | Claude Fable 5 | Anthropic | 85% | official ↗ | |
| #2 | Claude Mythos 5 | Anthropic | 85% | shared with Claude Fable 5 (same underlying model) | official ↗ |
| #3 | Gemini 3.5 Flash | Google DeepMind | 78.4% | official ↗ |
Frequently asked questions about OSWorld-Verified
What is the OSWorld-Verified benchmark?
Verified split of OSWorld — real computer-use GUI agent tasks.
How is the OSWorld-Verified benchmark scored?
OSWorld-Verified is scored using the success rate (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on OSWorld-Verified?
As of the latest reported scores on GenAIList, Claude Fable 5 achieves the highest result on OSWorld-Verified with a score of 85%.
Is a higher OSWorld-Verified score better?
Yes. On OSWorld-Verified a higher score indicates better performance, so models near the top of the leaderboard are the strongest.