// BENCHMARK

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.