KoALa-Bench - KCSAT: leaderboard
Metric: Accuracy (%) on the long-form listening questions of the Korean College Scholastic Ability Test (2006-2012 recordings, multiple choice), Korean speech synthesized or recorded per item, clean audio (first value of each clean / noisy pair), mean over four prompts with greedy decoding; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash Lite | 81.18 |
| 2 | Qwen3 Omni 30B A3B Instruct | 80.59 |
| 3 | Voxtral-Mini-3B-2507 | 69.41 |
| 4 | Gemma 3n E4B (IT) | 33.53 |
Interactive version: theaggregate.ai/benchmark?slug=koala-bench-kcsat · How It Works · Data refreshed daily, snapshot 2026-10-07.