List your company

Audio-Visual Captioning on DVD-Bench Zh

78AccuracyD-ORCA
54.80860.82966.8572.871Feb 8, 2026

Evaluation results

MethodLinks
D-ORCANumber of Parameters=8B2026.027817.537.8
Ours-SFT ModelNumber of Parameters=8B2026.0269.630.324.7
AVoCaDONumber of Parameters=7B2026.0269.3——
Qwen3-Omni-InstructNumber of Parameters=30B-A3B2026.0263.560.6—
ARC-Qwen-Video-NarratorNumber of Parameters=7B2026.0263.253.610.1
video-SALMONN 2+Number of Parameters=7B2026.0259.9——
Qwen2.5-OmniNumber of Parameters=7B2026.0255.769.4—