Model	Overall		Basic Following								Advanced Following												Designer
			Avg		Attribute		Relation		Reasoning		Avg		Attribute +Relation		Attribute +Reasoning		Relation +Reasoning		Style		Text		Real World
	short	long	short	long	short	long	short	long	short	long	short	long	short	long	short	long	short	long	short	long	short	long	short	long
Diffusion based Models (GPT-4o Evaluation)
FLUX.1 dev	63.47	67.32	70.03	71.84	77.75	78.80	78.02	78.67	54.31	58.04	62.69	65.11	66.95	69.74	60.99	60.75	62.47	64.66	63.33	72.67	43.25	58.91	64.14	63.65
SD 3	66.83	63.69	70.23	69.73	80.05	78.15	76.14	74.83	54.50	56.22	64.96	64.62	72.88	72.48	59.44	61.39	62.10	63.15	75.33	77.00	58.24	26.87	62.78	63.15
SD 3.5	69.59	64.96	71.74	70.07	80.25	78.35	78.61	75.61	56.38	56.24	66.90	62.69	73.41	68.33	60.73	57.30	64.51	62.95	78.33	71.67	71.79	49.76	62.28	64.39
SANA 1.5	65.17	62.17	70.18	69.03	76.85	75.25	78.73	77.60	54.97	54.23	65.75	62.45	72.42	68.66	63.84	61.76	63.69	60.66	93.00	81.00	16.91	14.13	66.13	66.25
Playground v2	46.30	54.63	53.10	63.31	55.75	67.00	63.44	73.87	40.11	49.06	44.97	54.82	50.90	63.34	39.48	49.99	46.95	54.37	69.33	81.67	1.10	2.16	49.63	50.25
Playground v2.5	46.34	54.04	54.33	63.04	57.75	69.25	63.32	74.07	41.90	45.79	45.41	54.31	53.14	63.90	39.69	49.52	46.40	52.45	65.33	80.00	1.48	5.08	48.01	46.28
PixArt-delta	43.32	48.92	50.62	55.52	50.55	54.90	62.86	68.07	38.44	43.60	42.05	47.37	47.45	51.38	37.40	43.00	43.50	48.74	66.33	85.67	0.19	1.15	43.18	43.80
PixArt-alpha	45.83	51.12	52.27	57.87	54.95	58.75	63.02	70.34	38.83	44.53	45.17	50.04	52.79	56.62	39.76	45.80	45.91	49.27	66.00	86.00	0.72	1.39	50.50	47.39
PixArt-sigma	58.17	58.80	64.88	67.21	70.30	75.00	71.59	74.88	52.75	51.75	58.80	58.09	65.13	65.74	56.08	54.86	58.28	56.80	89.33	87.33	3.45	3.88	56.58	58.93
LUMINA-Next	50.37	49.83	57.32	57.49	61.20	60.85	64.93	66.54	45.83	45.08	50.27	48.23	55.25	54.13	45.84	43.07	52.55	49.70	77.00	77.67	1.01	0.96	49.75	50.50
Hunyuan-DiT	50.22	53.63	61.92	64.57	66.85	71.35	70.92	73.45	48.00	48.92	52.86	52.94	61.37	59.52	49.99	48.51	53.41	53.71	55.67	81.67	0.62	1.01	45.16	44.54
AR based Models (GPT-4o Evaluation)
Llamagen	40.40	39.85	48.42	50.75	45.70	54.15	60.96	58.56	38.58	39.55	39.75	38.77	42.34	38.69	37.48	37.57	42.58	43.87	53.00	45.00	1.10	1.96	41.81	39.33
LightGen	52.77	46.31	61.49	51.68	65.90	58.80	69.26	54.94	49.30	41.31	54.01	46.14	59.16	48.93	52.38	45.41	55.29	47.55	67.00	58.00	2.63	6.47	53.97	55.33
Show-o	56.94	58.17	66.28	69.56	72.20	78.30	74.08	76.52	52.56	53.85	59.46	58.76	66.92	66.38	56.03	55.72	61.29	59.31	68.67	72.00	3.16	4.65	57.57	56.82
Infinity	63.11	60.83	69.55	67.02	75.70	76.15	78.18	74.27	54.77	50.63	64.58	60.95	70.98	68.94	62.25	58.42	63.87	58.33	81.00	79.67	21.17	19.54	60.05	61.54
Janus-Pro	64.41	62.19	70.97	68.15	77.10	76.55	76.84	76.45	58.98	51.45	64.93	62.87	71.76	71.59	61.88	59.57	64.48	60.46	71.00	68.33	32.14	33.19	65.51	62.16