AudioEst. 2024
AudioBench
AudioBench evaluates audio language models across speech understanding, audio scene analysis, and voice-based reasoning. It covers speech recognition, emotion detection, speaker identification, and audio event classification.
Metrics
Average score across audio understanding tasks
Created By
AudioLLMs Team
Paper
View paper →Website
Visit website →Top Model Scores
| Rank | Model | Score | Date |
|---|---|---|---|
| 1 | Gemini 3 Ultra | 87.3% | 2026-01 |
| 2 | GPT-5.2 Audio | 84.6% | 2026-03 |
| 3 | Whisper V4 | 82.1% | 2026-01 |
| 4 | Claude Opus 4.6 | 79.8% | 2026-02 |
| 5 | Qwen2-Audio | 76.4% | 2025-12 |