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 - IMDA 30s SQA Human — leaderboard

Metric: Mean Score (%). Source: github.com. 5 models tracked.

Top models

#ModelScore
1cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct62.95
2cascade_whisper_large_v3_llama_3_8b_instruct58.62
3Qwen2-Audio-7B-Instruct47.1
4SALMONN_7B42.3
5Qwen-Audio-Chat42.2

Interactive version: theaggregate.ai/benchmark?slug=audiobench-imda-30s-sqa-human · 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.