CASU - Entity Extraction: leaderboard
Metric: Accuracy (%; four-option multiple-choice questions on semi-synthetic auditory scenes that combine speech, sound events and background; entity extraction: identify the entity in the scene that explains an observation). Source: arxiv.org. Saturation forecast: Around December 2026. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.0 Flash | 72.77 |
| 2 | GPT-4o Audio | 70.98 |
| 3 | Qwen3 Omni 30B A3B Instruct | 68.85 |
| 4 | Qwen2.5-Omni-7B | 61.1 |
| 5 | SALMONN-13B | 50.96 |
| 6 | Voxtral-Small-24B-2507 | 41.67 |
| 7 | Qwen2-Audio-7B-Instruct | 40.81 |
Interactive version: theaggregate.ai/benchmark?slug=casu-entity-extraction · How It Works · Data refreshed daily, snapshot 2026-09-26.