Share your thoughts, 1 month free Claude Pro on usSee more

Spatial Reasoning on SPAR-Bench full

68.35Average Score

Ours-4B

Updated 1mo ago

Evaluation Results

Method
Ours-4B 2026.03	68.35	59.94	89.61	49.12	57.07	19.27	88.02	63.4	77.6	35.42	60.42	47.84	73	31.01	81.74	92.35	68.75	87.5	91.76	84.21	79.57	66.86	83.44	81.23
SPAR-8B 2026.03	63.25	65.53	81.53	79.22	38.25	35.51	78.93	79.18	68.13	63.5	63.01	78.88	73	37.14	61.29	86.47	79.76	64	69.23	59	47.31	50	42.38	53.5
VG-LLM-4B 2026.03	60.36	52.81	83.97	44.75	34.27	16.96	79.08	60.63	66.2	36.63	51.35	39.69	63	25.82	72.92	89.12	63.69	81.25	83.79	77.84	68.82	60.17	59.6	71.99
CroPond-7B 2025.12	53.64	19.22	23.33	27.81	21.51	21.24	5.34	14.79	21.21	18.52	66.55	79.39	80.25	40	79.94	69.41	61.9	89.75	89.01	87.53	75.81	76.74	82.45	86.83
CroPond-3B 2025.12	52.67	22	30.56	30.31	26.88	20.97	10.43	16.71	23.97	16.16	57.77	75.57	71	26.75	78.23	77.06	66.37	89.25	86.54	88.37	75	68.9	68.54	84.03
GPT-4V 2025.12	41.6	41.95	48.25	42.66	20.86	23.58	58.29	52.33	48.65	40.44	44.02	59.29	28.75	22.02	42.93	71.76	67.26	46.25	54.95	41	30.38	29.65	20.2	24.93
GPT-4o 2025.12	38.11	36.88	51.22	44.69	21.21	19.33	41.4	44.9	36.34	35.96	26.49	27.74	25.25	19.99	43.8	65	64.88	44.75	50.82	43.21	29.84	32.56	27.81	35.29
GPT-5 2026.03	37.4	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Qwen2.5-VL-72B 2025.12	37.01	29.94	37.47	43	19.52	18.36	38.72	36.44	27.8	18.25	44.61	56.49	32.75	17.27	43.8	58.82	61.9	40.75	53.57	45.98	26.88	35.17	34.11	36.97
Gemini-2.5-Pro 2026.03	36.3	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
InternVL2.5-8B 2025.12	36.28	29.46	25.78	29.31	23.79	18.76	46.82	42.68	22.62	25.89	31.88	61.32	28	6.32	43.8	59.71	56.85	51.75	44.23	41.55	36.56	41.57	22.52	39.5
InternVL2.5-8B 2026.03	36.28	29.46	25.78	29.31	23.79	18.76	46.82	42.68	22.62	25.89	31.88	61.32	28	6.32	43.8	59.71	56.85	51.75	44.23	41.55	36.56	41.57	22.52	39.5
InternVL2.5-26B 2025.12	34.11	24.18	41.83	36.28	18.09	17.96	22.62	17.97	22.01	16.63	50.11	69.47	30.75	7.03	42.4	62.94	58.33	45.25	54.67	50.97	24.46	25	27.48	32.49
InternVL2.5-38B 2025.12	33.83	26	42.03	38.81	17.1	17.77	17.58	17.84	29.37	27.51	30.89	44.53	17.25	9.7	44.13	69.12	66.67	43.75	64.29	37.67	25.27	31.98	31.79	26.61
Qwen2.5-VL-32B 2025.12	33.09	27.09	37.47	35.25	15.91	15.75	34.2	33.01	26.2	18.96	33.92	34.1	33.75	13.15	40.44	58.82	61.31	37.75	51.1	34.35	26.08	33.14	25.83	35.57
Qwen2.5-VL-7B 2025.12	33.07	28.75	31.33	33.66	21.99	14.97	42.88	37.73	23.83	23.64	22.97	33.33	28.75	6.83	40.27	58.24	51.49	44.75	50	32.13	33.87	32.85	27.15	31.93
Qwen2.5-VL-7B 2026.03	33.07	28.75	31.33	33.66	21.99	14.97	42.88	37.73	23.83	23.64	22.97	33.33	28.75	6.83	40.27	58.24	51.49	44.75	50	32.13	33.87	32.85	27.15	31.93
InternVL2-8B 2026.03	33.02	26.83	25.75	30.88	20.67	20.78	39.03	36.19	19.15	22.19	36.49	63.36	28	18.11	37.37	64.71	54.46	42.75	37.36	26.32	34.14	31.1	20.86	24.65
LLaVA-OV-7B 2026.03	31.2	21.79	30.33	26.94	18.58	13.87	10.43	13.64	31.24	29.29	26.13	38.68	30.25	9.47	40.14	56.47	55.06	37.25	48.63	38.23	30.38	33.72	26.49	35.01
InternVL2.5-4B 2025.12	30.55	25.66	29.06	32.97	21.77	16.83	20.84	26.85	28.13	28.79	29.75	47.07	33.25	8.92	35.16	54.12	58.93	35.5	29.67	34.63	24.73	31.39	19.21	28.29
InternVL2.5-2B 2025.12	30.14	25.79	39.67	39.72	12.12	15.03	30.94	29.59	20.22	19.02	22.93	37.91	24.25	6.64	36.41	51.47	56.85	50.25	33.79	24.1	27.15	35.17	26.49	22.41
LLaVA-v1.5-7B 2026.03	23.65	10.85	5.17	12.53	17.37	11.34	7.25	5.26	18.73	9.12	26.5	24.43	26.75	28.31	34.09	51.18	52.38	34.25	24.18	26.87	34.68	29.94	22.52	30.81
LLaVA-v1.6-7B 2026.03	13.21	8.53	12.14	0	20.35	0.27	10.76	0.41	24.27	0	4.79	6.62	7.75	0	20.18	51.76	7.74	6.25	32.14	6.37	39.52	10.47	21.52	5.88