List your company
ResearchFormerly WizWand

Multimodal Understanding on MMMU-Pro vision

45.84AccuracyMiMo-Embodied
22.710428.715234.7240.7248Jun 8, 2025Jul 5, 2025Aug 2, 2025Aug 29, 2025Sep 26, 2025Oct 23, 2025Nov 20, 2025
Updated 6mo ago

Evaluation results

MethodLinks
MiMo-EmbodiedParams=7B2025.1145.84
Claude 3.7 SonnetParams=–2025.1145.8
Perception-R1-7BBase Model Family=Qwen2.5-VL2025.0640.3
InternVL3Params=8B2025.1137.8
SophiaVL-R1-7BBase Model Family=Qwen2.5-VL2025.0637.6
Qwen2.5-VL-7B-IT + GRPOBase Model Family=Qwen2.5-VL, Instruction-Tuning=IT, Training Strategy=GRPO2025.0637.1
GPT-4oParams=–2025.1136.1
Vision-R1-7BBase Model Family=Qwen2.5-VL2025.0636
MiMo-VLParams=7B2025.1135.95
OpenVLThinker-7BBase Model Family=Qwen2.5-VL2025.0635.3
MM-Eureka-7BBase Model Family=Qwen2.5-VL2025.0635.2
VLAA-Thinker-7BBase Model Family=Qwen2.5-VL2025.0634.8
Qwen2.5-VL-7B-ITBase Model Family=Qwen2.5-VL, Instruction-Tuning=IT2025.0633.8
Perception-R1-Qwen2-7BBase Model Family=Qwen2-VL2025.0633.7
R1-Onevision-7BBase Model Family=Qwen2.5-VL2025.0630.7
Qwen2-VL-7B-IT + GRPOBase Model Family=Qwen2-VL, Instruction-Tuning=IT, Training Strategy=GRPO2025.0629.8
Qwen2.5-VLParams=7B2025.1129.4
Qwen2-VL-7B-ITBase Model Family=Qwen2-VL, Instruction-Tuning=IT2025.0626.6
R1-VL-7BBase Model Family=Qwen2-VL2025.0623.6