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

Video Spatial Reasoning on VSI-Bench

79.2Average Score

Human Level

Updated 22d ago

Evaluation Results

Method
Human Level 2026.03	79.2	84.3	47	60.4	45.9	94.7	95.8	95.8	100
SpaceMind++ 2026.05	73.2	74.5	62.4	77.9	76.9	73.5	89.7	48.2	84.1
SpaceMind 2026.05	70.2	73.9	61.5	77.6	74.8	67.7	88.6	46.9	70.7
SenseNova-SI-1.2 2026.05	69.6	72.7	56	77.1	75.7	70.4	81.7	42.8	79.9
VLM-3R 2026.05	60.9	70.2	49.4	69.2	67.1	65.4	80.5	45.4	40.1
VST-7B 2026.05	60.6	72	44.4	74.3	68.3	59.7	55.8	44.9	65.2
Thinking with Spatial Code + 2D box 2026.03	60	95.2	60.7	50.8	33.1	62	87.1	32.5	59
Qwen3VL-8B-Instruct 2026.05	57.9	67.5	47	76.3	61.9	58	50.9	35	66.3
Thinking with Spatial Code 2026.03	57	58.3	39	73	52.4	57.8	55.9	38.7	63.9
Thinking with Spatial Code (w/o RL) + 2D box 2026.03	56.5	95.2	50	50.9	19.9	63.7	55.5	25.3	58.4
Gemini-3 Pro 2026.05	56	49	42.8	71.5	41.8	56.6	57.5	61.9	60
GPT-5 2026.03	55	53.3	34.4	73.3	47.5	63.7	48.6	50.2	68.9
Qwen3-VL 2026.03	55	52.1	44.7	60.4	43.1	56.6	56.3	38.1	70.2
GPT-5 2026.05	55	53.3	34.4	73.3	47.5	63.7	48.6	50.2	68.9
Thinking with Spatial Code (w/o RL) 2026.03	54.6	58.3	37	71.2	52.4	54.2	50.2	35.6	63.9
Qwen3-VL + 2D box 2026.03	54.5	66.6	42.3	57.8	40.8	56.9	52.7	37.6	66.9
Gemini-2.5-Pro 2026.03	53.5	46	37.3	68.7	54.3	61.9	43.9	47.4	68.7
Qwen3-VL 2026.03	52.8	53.1	46.3	63.4	48	53.3	49.9	37.1	58.9
CoF-InternVL3-8B 2025.05	51.3	-	-	-	-	-	-	-	-
Seed-1.6 2026.03	49.9	43.5	34.3	66.1	52.8	55	35.7	44.3	67.9
Gemini-1.5 Pro 2026.03	48.8	49.6	30.9	64.1	49.4	51.3	48.1	42	68
Gemini-1.5-Pro 2025.05	48.8	-	-	-	-	-	-	-	-
InternVL3-78B 2026.05	48.5	71.2	53.7	44.4	39.5	55.9	39.5	28.9	54.5
Spatial-MLLM 2026.05	48.4	65.3	34.8	63.1	45.1	41.3	46.2	33.5	46.3
Grok-4 2026.05	47.9	37.1	32.9	60.8	45.4	53.1	39.6	47.4	66.8
Spatial-MLLM 2026.03	46.3	66.6	38	63.6	35.4	40.4	48.2	32.9	44.3
SpatialLadder 2026.03	44.8	62.1	35.3	61.9	41.4	45.6	46.4	27.3	38.5
SpaceR 2026.03	41.5	44.5	24.7	53.5	37.3	41.9	46.1	29.3	54.8
InternVL3-8B 2025.05	41	-	-	-	-	-	-	-	-
LLaVA-Video 2026.03	40.9	48.9	22.8	57.4	35.3	42.4	36.7	35	48.6
LLaVA-NeXT-Video-72B 2026.05	40.9	48.9	22.8	57.4	35.3	42.4	36.7	35	48.6
LLaVA-OneVision-72B 2025.05	40.2	-	-	-	-	-	-	-	-
LLaVA-OneVision 2026.03	40.2	43.5	23.9	57.6	37.5	42.5	39.9	32.5	44.6
LLaVA-OneVision-72B 2026.05	40.2	43.5	23.9	57.6	37.5	42.5	39.9	32.5	44.6
Qwen2-VL-72B 2025.05	37.6	-	-	-	-	-	-	-	-
CoF-InternVL2.5-4B 2025.05	36.9	-	-	-	-	-	-	-	-
LLaVA-NeXT-Video-7B 2025.05	35.6	-	-	-	-	-	-	-	-
LLaVA-Video 2026.03	35.6	48.5	14	47.8	24.2	43.5	42.4	34	30.6
GPT-4o 2026.03	34	46.2	5.3	43.8	38.2	37	41.3	31.5	28.5
GPT-4o 2025.05	34	-	-	-	-	-	-	-	-
InternVL2.5-4B 2025.05	33.5	-	-	-	-	-	-	-	-
LLaVA-OneVision-7B 2025.05	32.4	-	-	-	-	-	-	-	-
LLaVA-OneVision 2026.03	32.4	47.7	20.2	47.4	12.3	42.5	35.2	29.4	24.4
Qwen2.5-VL 2026.03	32.3	32.8	18.1	43.8	31.7	38	37.4	28.3	27.9
Qwen2-VL-7B 2025.05	31	-	-	-	-	-	-	-	-