SEA-SpeechBench - Age Recognition (English Prompt): leaderboard
Metric: Macro-F1 (%; speaker age group (teens, adults, seniors) from speech, labels canonicalised by bilingual string matching, per-dataset scores averaged; short clips of at most 30 s from curated public Southeast Asian speech corpora, up to 1,000 sampled items per dataset; English instruction prompt). Source: arxiv.org. Saturation forecast: Around 2029. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen3 Omni 30B A3B Instruct | 39.56 |
| 2 | Voxtral-Mini-3B-2507 | 37.26 |
| 3 | Gemini 2.5 Flash | 36.93 |
| 4 | GPT-4o Audio | 36.91 |
| 5 | Gemma 3n E4B (IT) | 32.41 |
| 6 | SeaLLMs-Audio-7B | 29.77 |
| 7 | gemma-3n-E2B-it | 26.82 |
| 8 | Phi-4 Multimodal Instruct | 26.28 |
| 9 | Qwen2-Audio-7B-Instruct | 17.23 |
| 10 | Qwen2.5-Omni-7B | 15.23 |
Interactive version: theaggregate.ai/benchmark?slug=sea-speechbench-age-recognition-english-prompt · How It Works · Data refreshed daily, snapshot 2026-09-26.