Our new X account is live! Follow @wizwand_team for updates

Vision-Language Evaluation on VIEScore

1.32CV (CIG-SC)

Gemini 2.5 Flash

Updated 4d ago

Evaluation Results

Method	Links
Gemini 2.5 Flash 2026.01		1.32	0.94	1.11	0.94	1.01	0.94	1.14	0.92	1	0.94	1.14	0.93	-	-	-	-	-	-	-	-	-	-	-	-
GPT-4o-mini 2026.01		0.56	0.93	0.82	0.93	0.52	0.94	0.58	0.93	1.11	0.95	0.3	0.93	-	-	-	-	-	-	-	-	-	-	-	-
GPT-4o 2026.01		0.46	0.93	0.3	0.96	0.37	0.95	1.02	0.94	0.32	0.94	0.68	0.92	-	-	-	-	-	-	-	-	-	-	-	-
Qwen3-235B-VL 2026.01		0.37	0.92	0.47	0.94	0.94	0.95	0.61	0.9	0.43	0.95	0.67	0.91	-	-	-	-	-	-	-	-	-	-	-	-
LLaMA-4-Maverick 2026.01		0.36	0.9	0.17	0.92	0.54	0.93	0.32	0.89	0.56	0.93	0.84	0.9	-	-	-	-	-	-	-	-	-	-	-	-
Qwen3-30B-VL 2026.01		0.32	0.94	0.62	0.94	0.45	0.94	0.4	0.94	0.64	0.93	0.16	0.92	-	-	-	-	-	-	-	-	-	-	-	-
LLaMA-4-Scout 2026.01		0.29	0.81	0.46	0.83	0.55	0.87	0.58	0.8	0.8	0.88	0.77	0.8	-	-	-	-	-	-	-	-	-	-	-	-
Gemini 2.5 Flash 2026.01		-	-	-	-	-	-	-	-	-	-	-	-	2.08	0.45	3.35	0.51	1.87	0.55	1.56	0.49	1.99	0.51	3.86	0.61
GPT-4o 2026.01		-	-	-	-	-	-	-	-	-	-	-	-	1.92	0.47	3.03	0.5	2.42	0.43	1.98	0.39	2.06	0.51	4.4	0.6
GPT-4o-mini 2026.01		-	-	-	-	-	-	-	-	-	-	-	-	1.48	0.45	3.11	0.43	1.96	0.55	1.84	0.43	2.29	0.45	4.14	0.52
Qwen3-30b-VL 2026.01		-	-	-	-	-	-	-	-	-	-	-	-	1.74	0.46	3.09	0.46	2.15	0.49	1.75	0.43	2.2	0.47	3.75	0.6
Qwen3-235b-VL 2026.01		-	-	-	-	-	-	-	-	-	-	-	-	1.37	0.57	2.61	0.56	1.79	0.56	1.73	0.43	2.09	0.5	3.92	0.58
Llama-4-Maverick 2026.01		-	-	-	-	-	-	-	-	-	-	-	-	1.48	0.43	2.76	0.42	2	0.56	1.28	0.45	1.85	0.52	3.47	0.53
Llama-4-Scout 2026.01		-	-	-	-	-	-	-	-	-	-	-	-	0.86	0.38	2.03	0.33	1.6	0.52	1.12	0.47	1.71	0.51	3.91	0.58