SEA-SpeechBench - Spoken QA (SEA Prompt): leaderboard
Metric: Judge score (0-100): short answers to questions about long-form Southeast Asian speech from YODAS2, rated 0-5 by a GPT-4.1 judge and multiplied by 20; instruction prompt in the native Southeast Asian language. Source: arxiv.org. Saturation forecast: Around December 2026. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash | 86.21 |
| 2 | Qwen3 Omni 30B A3B Instruct | 85.62 |
| 3 | GPT-4o Audio | 82.44 |
| 4 | Voxtral-Mini-3B-2507 | 79.06 |
| 5 | Gemma 3n E4B (IT) | 78.89 |
| 6 | SeaLLMs-Audio-7B | 78.38 |
| 7 | Qwen2.5-Omni-7B | 75.57 |
| 8 | Qwen2-Audio-7B-Instruct | 57.95 |
| 9 | gemma-3n-E2B-it | 56.06 |
| 10 | Phi-4 Multimodal Instruct | 47.36 |
Interactive version: theaggregate.ai/benchmark?slug=sea-speechbench-spoken-qa-sea-prompt · How It Works · Data refreshed daily, snapshot 2026-09-26.