RAIL - Acquired Knowledge: leaderboard
RAIL is a CHC-grounded auditory-intelligence benchmark for large audio-language models, organizing 32 subcapabilities into five cognitive dimensions over speech, sound and music. This board reports LLM-as-judge score (%) on acquired-knowledge tasks over speech, sound and music; higher is better.
Metric: LLM-as-judge score (%) on acquired-knowledge tasks over speech, sound and music; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 26 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 79.19 | #94 |
| 2 | Gemini 3 Flash | 76.63 | #164 |
| 3 | Gemini 2.5 Flash | 72.68 | #453 |
| 4 | MERaLiON-2-10B | 62.62 | #1640 |
| 5 | Gemma 3n E4B (IT) | 48.42 | #2210 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=rail-acquired-knowledge · How It Works · Data refreshed daily, snapshot 2026-11-13.