AppTek Call-Center Dialogues (Fixed 60s Chunks): leaderboard

AppTek Call-Center Dialogues (2026) is a long-form English speech recognition test set of spontaneous role-played call-center conversations in 14 accents, recorded for evaluation only. This board is the word error rate in percent, averaged over the accents, with audio cut into fixed 60-second chunks; lower is better.

Metric: Word error rate (%, averaged over the 14 accents) on AppTek Call-Center Dialogues (128.6 hours of spontaneous role-played English call-center conversations, 14 accents), default inference settings, scored per session after Open ASR Leaderboard text normalization, audio segmented with fixed 60-second chunks; lower is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen3-ASR-1.7B7.4
2Qwen3-ASR-0.6B8.7
3parakeet-tdt-0.6B-v29.4
4canary-qwen-2.5B10
5parakeet-tdt-0.6B-v312.1
6kyutai-stt-pytorch-stt-2.6B-en13.2
7canary-1B-v213.3
8granite-speech-3.3-8B13.8
9Phi-4 Multimodal Instruct18.8#4155
10granite-speech-3.3-2B19.7

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=apptek-call-center-dialogues-fixed-60s-chunks · How It Works · Data refreshed daily, snapshot 2026-11-22.