SEA-SpeechBench - Speech Translation (English Prompt): leaderboard
Metric: BLEU (0-100): corpus BLEU of the English translation of Southeast Asian speech; 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 | GPT-4o Audio | 21.24 |
| 2 | Voxtral-Mini-3B-2507 | 19.98 |
| 3 | Gemini 2.5 Flash | 16.86 |
| 4 | Qwen3 Omni 30B A3B Instruct | 15.28 |
| 5 | Gemma 3n E4B (IT) | 10.98 |
| 6 | SeaLLMs-Audio-7B | 10.74 |
| 7 | gemma-3n-E2B-it | 8.97 |
| 8 | Qwen2.5-Omni-7B | 7.91 |
| 9 | Qwen2-Audio-7B-Instruct | 4.54 |
| 10 | Phi-4 Multimodal Instruct | 3.04 |
Interactive version: theaggregate.ai/benchmark?slug=sea-speechbench-speech-translation-english-prompt · How It Works · Data refreshed daily, snapshot 2026-09-26.