ODU-Bench (Audio-Only) - Transcription: leaderboard
Transcription in ODU-Bench (Chen et al., 2026): accuracy of the transcript of the spoken demand, one minus the pooled character or word error rate, on the demand scenes of 731 synthetic audio-only scenes (user turns as audio, earlier assistant replies as text). Percent; higher is better.
Metric: Transcript accuracy (%; max(0, 1 - pooled CER or WER) of the demand transcript, demand scenes only; 731 synthetic audio-only scenes (570 with a demand, 161 without), user turns as audio, earlier assistant replies as text). Source: arxiv.org. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed 2.0 Lite | 93.2 | #286 |
| 2 | Gemini 3.1 Pro (Preview) | 91.7 | #91 |
| 3 | Qwen3 Omni 30B A3B Instruct | 91 | #902 |
| 4 | Qwen 3.5 Omni Plus | 89.3 | #237 |
| 5 | Gemini 3.7 Flash | 88.4 | #32 |
| 6 | Gemini 3.5 Flash Lite | 74.3 | #300 |
| 7 | Qwen2.5-Omni-7B | 69.4 | #1797 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=odu-bench-audio-only-transcription · How It Works · Data refreshed daily, snapshot 2026-11-12.