Search-based Grounding on WebEyes (test) benchmark leaderboard · SOTA2 Research

Search-based Grounding on WebEyes (test)

62.89Vehicles IoUGemini-1.5-Pro

Evaluation Results

Method	Links
Gemini-1.5-Pro2026.05		62.89	75	32.13	33.77	24.14	22.78	22.22	29.6	31.64	32	45.43	53.25	30.52	35.09
Doubao-Seed-2.0-Pro2026.05		60.73	75	29.04	32.47	36.32	39.24	27.37	40	38.32	43.2	52.76	63.64	35.69	44.41
Doubao-Seed-1.82026.05		55.87	69.44	30.25	35.06	31.72	32.91	24.98	36.8	37.35	41.6	47.73	57.14	33.28	41.3
Pixel-Searcher2026.05		54.74	58.33	23.53	24.68	38.81	43.04	29.68	42.8	35.94	38.4	42.12	48.05	34.17	41.3
Gemini-1.5-Flash2026.05		53.57	63.89	26.05	23.38	30.94	22.78	15.08	18	37.71	37.6	40.33	41.56	27.9	28.42
Doubao-Seed-1.62026.05		52.16	63.89	18.07	20.78	36.69	37.97	24.26	36	36.37	39.2	45.77	55.84	31.53	38.98
OneThinker-8B2026.05		51.19	61.11	28.19	32.89	23.86	24.05	21.81	32.81	37.71	42.4	33.92	38.96	32.78	38.7
Qwen2-VL-7B2026.05		47.58	58.33	20.13	25.97	24.78	29.11	22.3	28.4	32.54	36.8	31.17	37.66	26.81	32.61
Grounding-R12026.05		44.47	50	24.11	28.95	24.23	24.05	9.6	13.67	32.41	32.8	25.23	28.57	26.68	29.67
GPT-4o-mini2026.05		34.36	41.67	19.64	22.08	13.9	7.59	18.89	19.6	20.08	17.6	19.46	18.18	19.53	19.1
GPT-4V2026.05		30.01	27.78	3.95	1.3	6.59	6.33	1.61	0	6.29	2.4	13.15	7.79	6.38	3.88
UniVG-R12026.05		29.29	33.33	19.02	22.37	31.45	31.65	14.63	19.92	34.68	37.6	25.67	28.57	25.79	28.91
Perception-R12026.05		16.07	11.11	9.61	6.58	22.16	21.52	4.08	4	23.5	22.4	13.15	12.99	14.76	13.1
GPT-4o2026.05		13.94	2.78	1.14	0	1.09	0	1.47	0	0.17	0	6.59	2.6	2.44	0.47
InternVL2-8B2026.05		10.58	2.78	3.49	0	3.39	1.27	1.45	0	5.92	1.6	7.75	1.3	4.07	0.78