SEA-SpeechBench - Timestamped Content Query (60-120 s): leaderboard

Metric: WER or CER (%; transcribe only the speech inside a queried time window of a long recording of 60-120 seconds, CER for languages without word boundaries; English instruction prompt; blank where the model cannot take audio of that length; can exceed 100; lower is better). Source: arxiv.org. Saturation forecast: Around October 2026. 10 models tracked.

Top models

#ModelScore
1Qwen3 Omni 30B A3B Instruct1.34
2GPT-4o Audio7.38
3Gemini 2.5 Flash9.44
4Qwen2.5-Omni-7B9.85
5Voxtral-Mini-3B-250712.86
6Phi-4 Multimodal Instruct16.25

Interactive version: theaggregate.ai/benchmark?slug=sea-speechbench-timestamped-content-query-60-120-s · How It Works · Data refreshed daily, snapshot 2026-09-26.