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

Spatial Reasoning (Multi-Image) on MMSI-Bench

97.2Accuracy

Human

Updated 7d ago

Evaluation Results

Method	Links
Human 2025.10		97.2
Gemini-3-Pro-Preview 2026.03		45.2
GPT-5 2026.03		41.8
GPT-5 2025.10		40.7
Gemini-2.5-Pro 2026.03		38
Gemini-2.5-pro 2025.10		36.9
InternVL3.5-38B 2025.10		36.9
ViewFusion 2026.03		35.4
VST-7B-RL 2026.03		34.8
ViewFusion 2026.03		32.4
SpaceVista-7B 2025.10		32.3
VST-3B-RL 2026.03		32
Qwen2.5-VL-7B 2025.10		31.7
ViLAVT-7B 2026.02		31.3
Qwen3-VL-8B-Instruct 2026.03		31.1
InternVL3.5-8B 2025.10		30.9
Qwen2.5-VL-72B 2025.10		30.7
VILASR-7B 2026.02		30.2
ViLaSR-7B 2026.03		30.2
VILASR-7B 2025.10		30.2
Qwen3-VL-4B-Instruct 2026.03		30.1
SpaceVista-7B 2025.10		29.1
Qwen3-VL-2B-Instruct 2026.03		28.9
SpaceR-7B 2026.02		28.8
Qwen2.5-VL-3B-Instruct 2026.03		28.6
InternVL3-8B 2026.03		28
Spatial-MLLM-4B 2026.02		27.7
SpatialLadder-3B 2026.03		27.4
SpaceR-7B 2026.03		27.4
Qwen2.5-VL-7B 2025.10		27.3
Qwen2.5-VL-7B 2026.02		27.1
SpatialMLLM-4B 2025.10		27
Qwen2.5-VL-7B 2026.02		26.9
Qwen2.5-VL-7B-Instruct 2026.03		26.8
LLaVA-NeXT-Video-7B 2025.10		26.8
InternVL3-2B 2026.03		26.5
Spatial-MLLM-4B 2026.03		26.1
SpaceR-7B 2025.10		26.1
Cambrian-S-7B 2026.03		25.8
InternVL3-8B 2026.02		25.7
Cambrian-S-3B 2026.03		25.2
RandomChoice 2026.03		25
LLaVA-OneVision-7B 2026.02		24.5
LLAVA-Onevision-7B 2025.10		24.5