List your company
ResearchFormerly WizWand

Spatial Reasoning on MMSI

32.3ScoreQwen2.5-VL-7B + SAGE
23.87626.06328.2530.437Mar 11, 2026Mar 26, 2026Apr 10, 2026Apr 25, 2026May 10, 2026May 25, 2026Jun 10, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Qwen2.5-VL-7B + SAGEModel=Qwen2.5-VL-7B + SAGE2026.0532.3
Qwen3-VL-8BModel Parameters=8B2026.0631.1
GPT-4oModel=GPT-4o2026.0530.3
ViLASR-7BFT-Data=73K, Fine-tuned on identical training data=false2026.0330.2
Ouro-Spatial-4BModel Parameters=4B2026.0629.7
Ouro-Spatial-8BModel Parameters=8B2026.0629.3
SpatialLadder-3BModel=SpatialLadder-3B2026.0529.2
Qwen2.5-VL-3BFT-Data=-, Fine-tuned on identical training data=false2026.0328.6
Qwen3-VL-4BModel Parameters=4B2026.0628.3
VG-LLMFT-Data=385k, Fine-tuned on identical training data=false2026.0327.6
GeoSenseFT-Data=940K, Fine-tuned on identical training data=false2026.0327.5
SpaceR-sft-7BFT-Data=151K, Fine-tuned on identical training data=false2026.0327.4
SpatialLadder-3BFT-Data=26K, Fine-tuned on identical training data=false2026.0327.4
Cambrain-S-3BFT-Data=10M, Fine-tuned on identical training data=false2026.0327
Qwen2.5-VL-7BFT-Data=-, Fine-tuned on identical training data=false2026.0326.8
InternVL3-2BFT-Data=-, Fine-tuned on identical training data=false2026.0326.5
Qwen2.5-VL-7BModel=Qwen2.5-VL-7B2026.0526.4
InternVL-2.5-8BModel=InternVL-2.5-8B2026.0525.7
VG-LLM*FT-Data=940k, Fine-tuned on identical training data=true2026.0325.2
LLaVA-OV-7BModel=LLaVA-OV-7B2026.0524.5
Qwen2.5-VL-3B*FT-Data=940k, Fine-tuned on identical training data=true2026.0324.2