Agents

Eval

Train

Overview Leaderboard Evaluations Phases

MMAU — Results

Rank	Model	Score
1	gemini-3-1-pro	82.5
2	inkling	77.2

MMAU — Leaderboard

1 phaseActive

MMAU Leaderboard

No self-reported entries.

About

UMD GAMMA Lab's massive multitask audio understanding benchmark (Sakshi et al., 2024). 10,000 clips, 27 tasks across speech, sound, and music. Metric: % accuracy on test-mini. Apac…

Pages

Phases: 1Active
Participants: 1
Submissions: 2
Last Modified: Jul 16, 2026