ESCUCHA - Audio Instruction Following: leaderboard
Metric: Pass rate (%; 100 open-ended items whose instruction (keywords, length, word exclusion, openings or closings, formatting, style) is spoken in the audio, checked by a deterministic verifier; in-the-wild Spanish audio from 6.7 s to 85 min per question with multiple accents and non-normative speech; one shared system prompt for every model). Source: arxiv.org. Saturation forecast: Around March 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 12B (IT) | 60 |
| 2 | Gemini 2.5 Flash | 54 |
| 3 | Qwen2.5-Omni-7B | 54 |
| 4 | Voxtral-Mini-3B-2507 | 40 |
Interactive version: theaggregate.ai/benchmark?slug=escucha-audio-instruction-following · How It Works · Data refreshed daily, snapshot 2026-09-29.