Share your thoughts, 1 month free Claude Pro on usSee more

Emotion Assessment on EEmo-Bench 1.0 (test)

0.87Valence SRCC

Qwen2-VL-7B

Updated 1mo ago

Evaluation Results

Method	Links
Qwen2-VL-7B 2026.02		0.87	0.88	0.59	0.57	-0.04	-0.04	0.47	0.47
Deepseek-VL-7B-chat 2026.02		0.85	0.83	0.54	0.56	-0.5	-0.53	0.3	0.29
mPLUG-Owl3-7B 2026.02		0.85	0.86	0.56	0.53	-0.22	-0.07	0.4	0.44
EEmo-Logic 2026.02		0.85	0.84	0.71	0.7	0.46	0.41	0.67	0.65
Qwen3-VL-8B 2026.02		0.84	0.82	0.66	0.62	-0.26	-0.15	0.41	0.43
EEmo-Logic 2026.02		0.84	0.83	0.57	0.56	0.78	0.74	0.73	0.71
Qwen2.5-VL-7B 2026.02		0.8	0.74	0.46	0.46	0.32	0.31	0.53	0.5
Janus-Pro-7B 2026.02		0.76	0.76	0.54	0.38	-0.3	-0.23	0.33	0.3
LLaVA-OneVision-7B 2026.02		0.67	0.47	0.24	0.28	-0.19	-0.17	0.24	0.19
LLaVA-NEXT-8B 2026.02		0.58	0.57	0.38	0.37	-0.07	-0.05	0.3	0.3