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

Spatial Reasoning on BLINK (Dep., Spa., All)

93Spa. Score

InternVL2.5-78B

Updated 1mo ago

Evaluation Results

Method
InternVL2.5-78B 2026.05	93	-	-	82.3	-	29.9	54.1	-
GPT-5 2026.06	90.2	-	-	82.3	-	-	45.8	77.3
InternVL2.5-8B 2026.05	89.5	-	-	77.4	-	34.7	44.4	-
Qwen2.5-VL-72B 2026.05	88.8	-	-	81.5	-	31.4	53.4	-
Qwen2.5-VL-7B (+ GASP Full Model) 2026.05	88.8	-	-	80.7	-	35	53.4	-
GPT-o4-mini-2025-05-16 2026.01	88.11	79.03	83.57	-	-	-	-	-
Qwen2.5-VL-7B (+ GASP Correspondence) 2026.05	88.1	-	-	79	-	34.6	54.9	-
RoboBrain-32B-2.0 2026.01	87.41	79.84	83.63	-	-	-	-	-
RoboPIN 2026.06	87.4	-	-	87.1	-	-	72.9	89.5
Qwen2.5-VL-32B 2026.05	86	-	-	75	-	31.1	44.3	-
Qwen2.5-VL-32B-Instruct 2026.01	85.31	77.42	81.37	-	-	-	-	-
Gemini-2.5-Pro 2026.06	85.3	-	-	86.3	-	-	46.6	78.5
Gemini-2.5-Pro-preview-05-06 2026.01	84.62	79.03	81.83	-	-	-	-	-
Qwen3-VL 2026.06	84.6	-	-	85.5	-	-	51.1	88.4
Pelican-VL 2026.06	84.6	-	-	75	-	-	47.3	63.3
VG-LLM 2026.05	84.3	-	-	77.2	-	59.2	50.8	-
InternVL2.5-4B 2026.05	83.9	-	-	66.9	-	32.5	44.4	-
LLaVA-Onevision-7B 2026.05	83.9	-	-	75	-	24.4	55.6	-
GPT-4o-2024-11-20 2026.01	83.22	72.58	77.9	-	-	-	-	-
RoboBrain-7B-2.0 2026.01	83.22	84.68	83.95	-	-	-	-	-
VeBrain 2026.06	83.2	-	-	67.7	-	-	46.6	48.8
RoboBrain-7B 2025.08	81.8	-	64.6	75.8	45.1	-	-	-
InternVL3.5 2026.06	81.8	-	-	78.2	-	-	47.4	72.7
VeBrain-8B 2026.01	81.12	78.23	79.68	-	-	-	-	-
Qwen2.5-VL-7B (+ DL3DV) 2026.05	81	-	-	78.1	-	25.3	42	-
Claude-Sonnet-4-2025-05-14 2026.01	80.42	75.81	78.12	-	-	-	-	-
Embodied-R1 2025.08	80.4	-	66.4	76.6	57.4	-	-	-
RoboBrain2.0 2026.06	80.4	-	-	80.7	-	-	48.1	46.5
Qwen2.5-VL-7B (Baseline) 2026.05	80.2	-	-	78.9	-	26.5	41.5	-
Qwen2.5VL-3B 2025.08	79.7	-	61.7	66.9	55.7	-	-	-
Embodied-R1 w/o CS 2025.08	79.7	-	64.1	72.6	56.6	-	-	-
Gemini-2.5-Flash-preview-04-17 2026.01	79.02	77.42	78.22	-	-	-	-	-
Qwen2.5-VL-72B-Instruct 2026.01	78.32	74.19	76.26	-	-	-	-	-
RoboBrain-7B-1.0 2026.01	78.32	75.81	77.07	-	-	-	-	-
FSD-13B 2025.08	78.3	-	60.5	70.2	46.7	-	-	-
Embodied-SFT 2025.08	78.3	-	66.3	81.5	54.9	-	-	-
LLaVA-Onevision-72B 2026.05	78.3	-	-	78.2	-	44.6	53.4	-
Mimo-Embodied 2026.06	77.6	-	-	94.4	-	-	26.3	83.2
GPT-4o 2026.05	76.9	-	-	64.5	-	28.5	60.2	-
Embodied-R1 2026.06	76.9	-	-	79.8	-	-	40.6	50
Cambrain-8B 2026.05	74.8	-	-	51.6	-	26.2	36.8	-
Action-Sketcher-3B 2026.01	74.67	82.3	82	-	-	-	-	-
Cosmos-Reason1-7B 2026.01	73.43	63.71	68.57	-	-	-	-	-
GPT4V 2025.08	72.7	-	60.7	59.7	54.9	-	-	-
LLaVA-1.5-13B 2025.08	69.9	-	54.2	53.2	52.5	-	-	-
GPT4o 2025.08	69.2	-	65.9	74.2	59.8	-	-	-
Gemini-1.5-Pro 2026.05	67.1	-	-	50	-	34.6	41.3	-
Magma-8B 2026.01	66.43	65.32	65.88	-	-	-	-	-
SAT-Dynamic-13B 2025.08	66.4	-	57.5	73.4	45.9	-	-	-
RoboPoint-13B 2025.08	65.7	-	57.2	62.1	56.6	-	-	-
ASMv2-13B 2025.08	65	-	57.5	56.5	63.9	-	-	-
AoTD 2026.05	61.5	-	-	49.2	-	23.3	45.1	-
LLaVA-NeXT-Video-7B (+ DL3DV) 2026.05	54.5	-	-	44	-	9.2	42.5	-
LLaVA-NeXT-Video-7B (Baseline) 2026.05	53.1	-	-	44.4	-	11.5	42.1	-
LLaVA-NeXT-Video-7B (+ GASP Correspondence) 2026.05	49.2	-	-	46.7	-	17.6	44.4	-
VLM-3R 2026.05	48.3	-	-	47.6	-	40.1	50.1	-
LLaVA-NeXT-Video-7B (+ GASP Full Model) 2026.05	47.6	-	-	48.4	-	22	57.1	-
w/o Tools 2026.06	-	-	-	-	-	-	47.9	-
w/ Tools 2026.06	-	-	-	-	-	-	48.5	-
Think3D-4B 2026.06	-	-	-	-	-	-	48.7	-
Skill-3D-4B 2026.06	-	-	-	-	-	-	60.8	-
w/o Tools 2026.06	-	-	-	-	-	-	56.1	-
w/ Tools 2026.06	-	-	-	-	-	-	57.4	-
Think3D-8B 2026.06	-	-	-	-	-	-	61.7	-
Skill-3D-8B 2026.06	-	-	-	-	-	-	68.5	-