Model results
MMAU-Pro
Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.
Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.
Reviewed recommendation and limits
Use task breakdowns to examine reasoning over speech, sounds, music, spatial audio and multiple clips.
Separate native audio from caption cascades. Overall combines sample-weighted choice accuracy, Qwen2.5-7B judged answers and instruction-constraint success. Resolve exact evaluator and model revisions before comparing scores.. Imported groups below may use different protocols; this review does not certify each run. The site abstract and results artifact disagree on some scores. Public answers, embedding-based answer matching and model-judge parsing affect interpretation. Dataset license is noncommercial.
No comparable scores imported yet
A methodology review does not mean results are imported. Use the publisher sources above for current results. We do not infer scores or ranks from a benchmark’s reputation.