Image Generation on WISE-Verified benchmark leaderboard · SOTA2 Research

Image Generation on WISE-Verified

92Culture ScoreQwen-Image-Agent

Evaluation Results

Method	Links
Qwen-Image-Agent2026.06		92	91.67	93.33	83.33	86.67	90	90.2
Nano Banana Pro2026.06		89.75	81.67	93.33	81.67	86.67	87.5	87.6
GPT-Image-1.52026.06		89	69.17	88.33	80	75.83	77.5	82.5
Qwen-Image-2.02026.06		82.19	65	89.92	79.17	80	74.79	79.54
Bagel2026.06		78	63.33	56.67	37.5	55	50.83	62.8
FLUX.2-dev2026.06		66.5	56.67	65.83	36.67	52.5	37.5	56.5
Qwen-Image2026.06		62.75	52.5	55.83	34.17	48.33	25	51
Qwen-Image-25122026.06		59.5	47.5	60	35	49.17	25.83	49.9
Z-Image2026.06		54.75	46.67	50.83	32.5	47.5	17.5	45.3
FLUX.1-dev2026.06		52.25	40	53.33	17.5	37.5	24.17	41.6
UniWorld-V12026.06		51.5	49.17	55	22.5	40	16.67	42.6
SD-XL-0.92026.06		49.25	36.67	24.17	26.67	33.33	18.33	36.4
FLUX.2-klein2026.06		49	39.17	55	38.33	48.33	22.5	44
SD-3.5-large2026.06		49	40.83	44.17	30	37.5	20.83	40.4
SD-3.5-medium2026.06		48.25	37.5	37.5	18.33	39.17	20	37.6
SD-3-medium2026.06		47	40.83	40	20	37.5	25.83	38.5
FLUX.1-schnell2026.06		46.5	32.5	46.67	20.83	38.33	10	36.4
SD-1.52026.06		44.5	30.83	20.83	20.83	21.67	15	30.9
FLUX.2-klein2026.06		44	36.67	46.67	31.67	39.17	33.33	40.1
Bagel2026.06		41.25	35	30.83	20	44.17	25.83	35.2
Janus-Pro2026.06		37	35	28.33	28.33	40	23.33	33.4
Janus2026.06		31.75	28.33	18.33	22.5	34.17	18.33	27.3
Janus-Pro2026.06		30.5	23.33	23.33	21.67	30.83	20	26.5