Image-based Audio-Visual Segmentation Quality Assessment on MQ-RAVSBench (Seen) benchmark leaderboard · SOTA2 Research

Image-based Audio-Visual Segmentation Quality Assessment on MQ-RAVSBench (Seen)

0.249RMSE (Perfect)Video-LLaMA3-7B

Evaluation Results

Method	Links
Video-LLaMA3-7B2026.02		0.249	0.268	0.291	0.283	0.313	0.272	0.301	0.573	0.957	0.39	86.76	0.57	0	0	0	0	0	0.2	0.42	9.77	89.48	0.86	0	0.57	0	0.29	0	0	0	10.13
Qwen2.5-Omni-7B2026.02		0.315	0.342	0.359	0.351	0.365	0.354	0.352	0.541	0.904	0.432	88.32	10.91	14.71	0	0	0	0	0.72	12.35	14.11	88.12	11.46	0	7.05	0	5.66	0	4.96	12.35	14.4
MQ-Auditor2026.02		0.359	0.199	0.16	0.298	0.232	0.329	0.305	0.334	0.507	0.303	60.58	83.41	91.78	59.92	78.39	36.09	47.15	74.55	69.43	66.81	60.58	29.35	85.78	24.74	71.57	20.04	44.08	43	74.52	50.41
Gemini-3-Flash-Preview2026.02		0.399	0.363	0.338	0.327	0.297	0.347	0.308	0.304	0.251	0.326	20.57	77.78	79	0.57	3.13	3.41	3.99	73.98	80.4	38.09	20.57	20.04	62.12	23.97	38.05	24.74	47.11	68.32	88.39	43.7
Ming-Flash-Omni2026.02		0.997	0.875	0.81	0.859	0.761	0.86	0.762	0.613	0.543	0.787	2.29	6.24	5.68	0	0	0.29	0.29	24.13	18.21	6.35	1.43	0.86	4.84	1.43	3.71	0.57	3.99	64.21	68.91	16.66