List your company

General Reasoning on MMMU

85.4Overall ScoreGPT5
18.652835.981453.3170.6386Jan 31, 2026Feb 25, 2026Mar 22, 2026Apr 17, 2026May 12, 2026Jun 6, 2026Jul 2, 2026

Evaluation results

MethodLinks
GPT5Model Category=Proprietary Model2026.0785.4
Gemini-2.5-ProModel Category=Proprietary Model2026.0784
ViLoMemBackbone=InternVL-3.5-8B, Augmentation=ViLoMem2026.0175.4
InternVL-3.5-8BBackbone=InternVL-3.5-8B, Augmentation=None2026.0174.7
PolarMemBackbone=InternVL-3.5-8B, Augmentation=PolarMem2026.0174.1
Vanilla RAGBackbone=InternVL-3.5-8B, Augmentation=Vanilla RAG2026.0173.4
ViLoMemBackbone=QWEN2.5-VL-32B, Augmentation=ViLoMem2026.0169.1
QWEN2.5-VL-32BBackbone=QWEN2.5-VL-32B, Augmentation=None2026.0168.4
Vanilla RAGBackbone=QWEN2.5-VL-32B, Augmentation=Vanilla RAG2026.0167.2
ViLoMemBackbone=InternVL-3.5-4B, Augmentation=ViLoMem2026.0167
PolarMemBackbone=QWEN2.5-VL-32B, Augmentation=PolarMem2026.0166.5
InternVL-3.5-4BBackbone=InternVL-3.5-4B, Augmentation=None2026.0166.5
PolarMemBackbone=InternVL-3.5-4B, Augmentation=PolarMem2026.0165.5
Vanilla RAGBackbone=InternVL-3.5-4B, Augmentation=Vanilla RAG2026.0164.7
LoMoModel=Qwen3.5-9B, Evaluation Protocol=Standard Evaluation2026.0563
LoMoModel=Qwen3.5-9B, Evaluation Protocol=Rendered Evaluation2026.0562.48
LASERModel Category=Open-source Vision-Language Model2026.0762.1
Reflection-V-7BModel Category=Open-source Vision-Language Model2026.0761.3
VAPO-Thinker-7BModel Category=Open-source Vision-Language Model2026.0760.2
Standard SFTModel=Qwen3.5-9B, Evaluation Protocol=Standard Evaluation2026.0559.44
ViLoMemBackbone=QWEN2.5-VL-7B, Augmentation=ViLoMem2026.0158.6
VisionR1-7BModel Category=Open-source Vision-Language Model2026.0757.6
QWEN2.5-VL-7BBackbone=QWEN2.5-VL-7B, Augmentation=None2026.0156.3
PolarMemBackbone=QWEN2.5-VL-7B, Augmentation=PolarMem2026.0155.7
Vanilla RAGBackbone=QWEN2.5-VL-7B, Augmentation=Vanilla RAG2026.0155.4
R1-Onevision-7BModel Category=Open-source Vision-Language Model2026.0754.3
ViLoMemBackbone=DeepSeek-VL2, Augmentation=ViLoMem2026.0154
Qwen2.5-VL-7BModel Category=Open-source Vision-Language Model2026.0752.7
VLAA-Thinker-7B2026.0552.1
EvoLMM2026.0551.9
DUELRole=Solver2026.0551.9
OpenVLThinker-7B2026.0551.8
Standard SFTModel=LLaVA-OV1.5-8B, Evaluation Protocol=Standard Evaluation2026.0551.78
Vision-Zero(CLEVR)2026.0551.7
MM-UPT2026.0551.5
DUELRole=Challenger2026.0551.4
LoMoModel=LLaVA-OV1.5-8B, Evaluation Protocol=Standard Evaluation2026.0551.22
Qwen2.5-VL-7B2026.0551.2
DeepSeek-VL2Backbone=DeepSeek-VL2, Augmentation=None2026.0151.1
ViLoMemBackbone=LLaVA-Next-Llama-3-8B, Augmentation=ViLoMem2026.0151
ViLoMemBackbone=DeepSeek-VL2-Small, Augmentation=ViLoMem2026.0150.8
Vanilla RAGBackbone=DeepSeek-VL2, Augmentation=Vanilla RAG2026.0150.6
PolarMemBackbone=DeepSeek-VL2, Augmentation=PolarMem2026.0150.4
Standard SFTModel=Qwen3.5-9B, Evaluation Protocol=Rendered Evaluation2026.0549.52
PolarMemBackbone=LLaVA-Next-Llama-3-8B, Augmentation=PolarMem2026.0149.1
Vanilla RAGBackbone=DeepSeek-VL2-Small, Augmentation=Vanilla RAG2026.0149
InternVL2.5-8BModel Category=Open-source Vision-Language Model2026.0749
LLaVA-Next-Llama-3-8BBackbone=LLaVA-Next-Llama-3-8B, Augmentation=None2026.0148.8
PolarMemBackbone=LLaVA-Next-Mistral-7B, Augmentation=PolarMem2026.0148.6
DeepSeek-VL2-SmallBackbone=DeepSeek-VL2-Small, Augmentation=None2026.0148.3
Vanilla RAGBackbone=LLaVA-Next-Llama-3-8B, Augmentation=Vanilla RAG2026.0148
ViLoMemBackbone=LLaVA-Next-Mistral-7B, Augmentation=ViLoMem2026.0147.8
PolarMemBackbone=DeepSeek-VL2-Small, Augmentation=PolarMem2026.0147.6
LLaVA-Next-Mistral-7BBackbone=LLaVA-Next-Mistral-7B, Augmentation=None2026.0146.3
Vanilla RAGBackbone=LLaVA-Next-Mistral-7B, Augmentation=Vanilla RAG2026.0145.4
LoMoModel=LLaVA-OV1.5-8B, Evaluation Protocol=Rendered Evaluation2026.0535.56
Standard SFTModel=LLaVA-OV1.5-8B, Evaluation Protocol=Rendered Evaluation2026.0521.22