GlobeAudio - Chinese: leaderboard
The Chinese portion of GlobeAudio (2026), a benchmark of multiple-choice questions written by native speakers about naturally occurring audio: accuracy in percent with the audio fed to the model directly. Higher is better.
Metric: Chinese (1,072 questions) accuracy (%) on GlobeAudio's naturalistic-audio multiple-choice questions written by native speakers; audio fed to the model directly, source-language prompts, predicted option label against the key. Source: arxiv.org. Saturation forecast: Around February 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 70.34 | #94 |
| 2 | MiMo-V2.5 | 57.6 | #354 |
| 3 | Gemini 2.0 Flash | 55.13 | #704 |
| 4 | Voxtral-Small-24B-2507 | 51.77 | #1291 |
| 5 | MERaLiON-2-10B | 48.79 | #1640 |
| 6 | Gemma 3n E4B (IT) | 45.62 | #2210 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=globeaudio-chinese · How It Works · Data refreshed daily, snapshot 2026-11-13.