List your company
ResearchFormerly WizWand

Visual Question Answering on RoboSpatial-Home

78.1AccuracySpatialThinker-30B
51.5858.46565.3572.235Nov 10, 2025
Updated 3mo ago

Evaluation results

MethodLinks
SpatialThinker-30BTraining Dataset=STVQA-7K, Training Protocol=RL with Dense Rewards (Ours)2025.1178.1
SpatialThinker-7BTraining Dataset=STVQA-7K, Training Protocol=RL with Dense Rewards (Ours)2025.1176.3
Qwen2.5-VL-7B + Vanilla GRPOTraining Dataset=STVQA-7K, Training Protocol=Vanilla GRPO2025.1176.2
Qwen2.5-VL-7B + SFTTraining Dataset=STVQA-7K, Training Protocol=SFT2025.1172.4
GPT-5-0807Model Category=Proprietary and Open-Source MLLMs2025.1171.5
Qwen2.5-VL-7BModel Category=Proprietary and Open-Source MLLMs2025.1170.6
SpatialThinker-3BTraining Dataset=STVQA-7K, Training Protocol=RL with Dense Rewards (Ours)2025.1170.6
Qwen2.5-VL-3B + SFTTraining Dataset=STVQA-7K, Training Protocol=SFT2025.1169.8
Claude-4-Sonnet-0514Model Category=Proprietary and Open-Source MLLMs2025.1169.7
VLAA-Thinker-7BModel Category=Proprietary and Open-Source MLLMs2025.1168.9
SpaceOmModel Category=Proprietary and Open-Source MLLMs2025.1168.9
GPT-4o-0513Model Category=Proprietary and Open-Source MLLMs2025.1168.4
Qwen2.5-VL-3B + Vanilla GRPOTraining Dataset=STVQA-7K, Training Protocol=Vanilla GRPO2025.1164
Qwen2.5-VL-3BModel Category=Proprietary and Open-Source MLLMs2025.1158.7
Claude-3.5-Sonnet-0620Model Category=Proprietary and Open-Source MLLMs2025.1157
Qwen3-VL-30BModel Category=Proprietary and Open-Source MLLMs2025.1153.1
SpaceThinkerModel Category=Proprietary and Open-Source MLLMs2025.1152.6