List your company

Spoken Dialogue Evaluation on URO-Bench English Basic Track

1.08Repeat RateMiMo-Audio
-2.789223.327949.44575.5621Feb 10, 2026

Evaluation results

MethodLinks
MiMo-Audio2026.021.0887.7471.2979.3457.6245.5923.1684.9267.2782.94
MoshiSetting=Autonomous full-duplex2026.021.2638.196.7139.538.373.0947.6448.4840.648.18
Qwen2.5-Omnisourced_from=Wu et al., 2025a2026.0228.3680.5189.9972.962.0363.5280.0478.1672.477.92
Freeze-OmniSetting=Autonomous full-duplex2026.0229.9620.110.6625.3144.751.218.8352.1648.352.95
Freeze-Omnisourced_from=Yan et al., 20252026.0270.8978.8726.2957.7446.952.8142.5652.2348.755.8
Kimi-Audiosourced_from=Wu et al., 2025a2026.0290.2778.1981.6370.8853.90.9743.563.0551.466.63
GLM-4-Voicesourced_from=Yan et al., 20252026.0290.9591.0764.4773.859.2830.9357.8280.7763.0778.76
Covo-Audio-Chat-TTSvoice_source=dialogue voice transferred from a TTS speaker2026.0292.7188.6487.2482.3263.6777.7874.5884.4979.1387.09
Step-Audio-AQAAvariant=AQAA, sourced_from=Wu et al., 2025a2026.0293.0290.6286.85362.338.27171.8675.5368.79
Covo-Audio-Chat-FDSetting=Autonomous full-duplex2026.0294.6483.4573.8280.864.5180.4774.7684.2575.0788.34
Covo-Audio-Chat2026.0295.2487.2389.1182.5967.685.6877.7885.7379.6786.82
GPT-4o Audiosourced_from=Yan et al., 20252026.0297.1694.137284.2782.67808095.294.1395.2
Fun-Audio-Chat2026.0297.1891.9876.1379.9766.6862.0879.6689.2178.8387.91
Qwen3-Omni2026.0297.3696.1681.392.2770.79.4550.8582.9575.3785.5
Step-Audio 2sourced_from=Wu et al., 2025a2026.0297.7483.990.7676.3865.4562.8377.0281.7472.8781.62
Step-Audio 2 minivariant=mini2026.0297.8184.6985.1573.1760.4528.1274.0177.7262.6379.66