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

Emotional Intelligence Evaluation on EIBench Basic 1.0 (test)

69.68Happy Score (LLaMA-3)

CFSA

Updated 1mo ago

Evaluation Results

Method	Links
CFSA 2025.04		69.68	68.72	61.08	61.14	68.39	69.46	72.63	70.31	68.81	68.04
LLaVA-NEXT (7B) 2025.04		64.32	61	48.6	46.74	58.75	53	62.99	59.39	58.8	54.97
Claude-3-haiku 2025.04		59.2	60.28	49.87	49.84	67.21	63.26	67.55	68.1	63.24	62.41
LLaVA-1.5 (13B) 2025.04		59.01	57.52	45.44	41.88	55.16	48.64	57.46	58.73	54.37	52.2
LLaVA-NEXT (13B) 2025.04		57.17	55.18	43.16	37.93	54.16	45.42	59.38	55.29	54.33	48.79
Video-LLaVA 2025.04		56.77	58.79	43.65	43.86	54.25	55.12	55.35	59.42	52.63	54.85
Video-LLaVA 2025.04		55.55	53.28	40.42	36.97	50.62	45.25	51.78	52.23	49.26	47.06
MiniGPT-v2 2025.04		55.11	60.04	47.95	51	62.29	64.24	51.55	57.9	54.05	58.37
LLaVA-NEXT (34B) 2025.04		54.5	51.03	38.96	35.65	51.1	47.21	51.77	52.04	49.03	47.13
LLaVA-NEXT (7B) 2025.04		54.16	49.24	43.71	39.87	53.29	46.52	58.9	53.06	53.82	48.18
ChatGPT-4o 2025.04		52.94	50.78	42.12	35.33	49.79	46.42	53.48	54.53	49.99	47.93
MiniGPT-v2 2025.04		52.78	51.8	47.1	47.76	60.47	58.14	50.78	53.66	52.89	53.59
LLaMA-3 (8B) 2025.04		52.36	50.73	34.78	32.71	52.29	46.87	43.62	42.06	44.73	41.94
ChatGPT-4V 2025.04		52.3	55.74	48.93	48.57	45	44.42	46.38	49.9	46.86	48.58
Otter 2025.04		45.63	49.25	42.53	43.07	47.67	46.19	39.47	48.3	42.81	46.64
Claude-3-sonnet 2025.04		44.58	44.45	38.95	42.86	55.98	54.4	61.41	62.24	54.1	54.89
Qwen-VL-Chat 2025.04		41.94	46.34	32.71	31.91	41.82	44.16	38.65	43.84	38.47	41.54
Qwen-VL-Chat 2025.04		32.09	39.68	22.32	26.1	30.64	33.88	25.02	36.32	26.45	33.65
Qwen-vl-plus 2025.04		29.05	27.22	23.58	17.89	38.35	30.08	30.09	26.87	31	25.9