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 - CoVoST2 ZH-EN BLEU — leaderboard

Metric: Mean Score (%). Source: github.com. 11 models tracked.

Top models

#ModelScore
1Phi-4 Multimodal Instruct22.68
2Qwen2-Audio-7B-Instruct16.47
3SALMONN-7B5.3

Interactive version: theaggregate.ai/benchmark?slug=audiobench-covost2-zh-en-bleu · 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.