OSWorld
We show this table for reference; we do not rank on it.
A computer-use benchmark for GUI task completion across the broader OSWorld task suite.
Benchmark score on OSWorld — September 27, 2026
We compile the OSWorld rows from provider self-reports. Claude Opus 4.5 leads the table at 66.3%, followed by Nemotron 3 Nano Omni 30B A3B (47.4%). We do not use these results to rank models overall.
Claude Opus 4.5
Anthropic
Nemotron 3 Nano Omni 30B A3B
NVIDIA
2 modelsAgenticCurrentDisplay onlyUpdated September 27, 2026
Benchmark score table (2 models)
ScoreAbout OSWorld
Year
2026
Tasks
Computer-use tasks
Format
Interactive GUI evaluation
Difficulty
Broad computer-use suite
BenchLM tracks plain OSWorld as a display-only provider-table reference and preserves OSWorld-Verified as the weighted core benchmark key.
Freshness and provenance
Version
OSWorld 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does OSWorld measure?
A computer-use benchmark for GUI task completion across the broader OSWorld task suite.
Which model scores highest on OSWorld?
Claude Opus 4.5 by Anthropic currently leads with a score of 66.3% on OSWorld.
How many models are evaluated on OSWorld?
2 AI models have been evaluated on OSWorld on BenchLM.
Compare top models on OSWorld
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.