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 Part 2 ASR WER — leaderboard

Metric: WER (%) (lower is better). Source: github.com. 10 models tracked.

Top models

#ModelScore
1Qwen2-Audio-7B-Instruct19.06
2Phi-4 Multimodal Instruct34.7
3SALMONN-7B42.35

Interactive version: theaggregate.ai/benchmark?slug=audiobench-imda-part-2-asr-wer · 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.