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 - TED-LIUM 3 Long Form WER — leaderboard

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

Top models

#ModelScore
1Phi-4 Multimodal Instruct3.82
2Qwen2-Audio-7B-Instruct8.74
3SALMONN-7B14.23

Interactive version: theaggregate.ai/benchmark?slug=audiobench-ted-lium-3-long-form-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.