AudioProcessBench - Semantic Errors: leaderboard
Metric: Type-conditioned PRMScore (0-100): detection of steps with semantic errors (misreading speech content or meaning) while keeping correct steps, other error types left out; 3,872 reasoning traces (23,497 steps, 41% erroneous) from six audio and omni models on MMAR, MMSU and MMAU-Pro questions, steps labelled by two LLM annotators with human review; few-shot critic prompt with three annotated example chains, temperature 0.7; higher is better. Source: arxiv.org. Saturation forecast: Around May 2028. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 69 |
| 2 | Gemma 3n E4B | 56.6 |
| 3 | Gemma 4 E4B | 55.2 |
| 4 | Phi-4 Multimodal Instruct | 50.3 |
| 5 | Gemma 3n E2B | 47.6 |
| 6 | Qwen2.5-Omni-7B | 44 |
| 7 | Gemma 4 E2B | 38.9 |
Interactive version: theaggregate.ai/benchmark?slug=audioprocessbench-semantic-errors · How It Works · Data refreshed daily, snapshot 2026-09-29.