Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

AudioBench - MMAU Speech — leaderboard

Metric: Mean Score (%). Source: github.com. 10 models tracked.

Top models

#ModelScore
1Qwen2-Audio-7B-Instruct46.02
2Gemini 1.5 Flash43.69
3Phi-4 Multimodal Instruct42.34
4SALMONN-7B32.73

Interactive version: theaggregate.ai/benchmark?slug=audiobench-mmau-speech · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.