Benchmark

OSWorld Extended

OSWorld is a scalable, real computer environment benchmark for evaluating multimodal agents on open-ended tasks across Ubuntu, Windows, and macOS. It…

Modality
multimodal
Categories
multimodal, reasoning, general, agents
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Claude 3.5 SonnetAnthropic0.222024-10-22evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.