Multi-image context generation on MICON-Bench benchmark leaderboard · SOTA2 Research

Multi-image context generation on MICON-Bench

98.85Object ScoreGPT-Image

Evaluation Results

Method	Links
GPT-Image2026.02		98.85	97.25	83.7	85.26	91.08	81.58	90.77
Qwen-Image-Edit-25072026.02		98.03	97.57	65.05	57.12	74.95	60.74	77.26
Nano-Banana2026.02		97.88	98.18	72.03	79.41	83.71	79.06	86.63
Qwen-Image-Edit-25072026.02		96.52	88.8	78.04	42.68	72.08	63.81	72.96
GPT-Image2026.02		96.45	94.41	93.39	87.69	90.15	85.99	91.51
Nano-Banana2026.02		95.6	93.79	92.13	84.23	83.13	82.84	89.25
OmniGen2 + DAR2026.02		89.84	81	82.12	48.72	59.28	60.73	69.21
BAGEL + DAR2026.02		89.56	91.57	72.39	66.05	80.33	60.93	78.29
OmniGen22026.02		89.52	80.32	81.64	44.76	57.96	60.96	67.83
OmniGen2 + DAR2026.02		89.5	83.06	70.71	49.79	72.26	61.15	71.22
BAGEL2026.02		89.08	89.32	69.05	59.57	72.39	54.32	73.78
DreamOmni22026.02		88.95	81.69	62.64	65.52	81.01	59.94	75.26
OmniGen22026.02		88.77	81.91	69.13	47.53	69.98	57.37	69.38
DreamOmni22026.02		88.24	84.76	85.28	59.64	76.16	59.58	75.56
BAGEL + DAR2026.02		88.04	91.88	90.76	56.06	71.24	66.34	76.31
BAGEL2026.02		87.64	89.96	89.84	52.4	64.64	65.09	73.55
UNO2026.02		62.3	57.75	55.11	27.56	28.47	38.17	43.87
UNO2026.02		58.4	66.68	65.28	28.84	20.96	39.08	44.76