SOTAVerified

Multimodal Reasoning

Reasoning over multimodal inputs.

Papers

Showing 125 of 302 papers

TitleStatusHype
Emerging Properties in Unified Multimodal PretrainingCode9
Skywork R1V2: Multimodal Hybrid Reinforcement Learning for ReasoningCode7
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement LearningCode7
LLaVA-CoT: Let Vision Language Models Reason Step-by-StepCode7
Skywork-R1V3 Technical ReportCode7
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-ThoughtCode7
Kimi-VL Technical ReportCode5
DeepEyes: Incentivizing "Thinking with Images" via Reinforcement LearningCode5
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future FrontiersCode5
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language ModelsCode5
R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT ModelCode4
R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal FormalizationCode4
R1-Onevision:An Open-Source Multimodal Large Language Model Capable of Deep ReasoningCode4
MiMo-VL Technical ReportCode4
MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level SupervisionCode4
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement LearningCode4
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RLCode4
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning ModelsCode4
Affordable AI Assistants with Knowledge Graph of ThoughtsCode3
Audio-Reasoner: Improving Reasoning Capability in Large Audio Language ModelsCode3
Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language ModelsCode3
Aguvis: Unified Pure Vision Agents for Autonomous GUI InteractionCode3
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World KnowledgeCode3
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented GenerationCode3
MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language ModelsCode3
Show:102550
← PrevPage 1 of 13Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GPT-4VAccuracy24Unverified
2Gemini ProAccuracy13.2Unverified
3LLaVa-1.5-13BAccuracy1.8Unverified
4LLaVa-1.5-7BAccuracy1.5Unverified
5BLIP2-FLAN-T5-XXLAccuracy0.9Unverified
6QWENAccuracy0.9Unverified
7CogVLMAccuracy0.9Unverified
8InstructBLIPAccuracy0.6Unverified
#ModelMetricClaimedVerifiedStatus
1GPT4VAccuracy22.76Unverified
2Gemini ProAccuracy17.66Unverified
3Qwen-VL-MaxAccuracy15.59Unverified
4InternLM-XComposer2-VLAccuracy14.54Unverified
#ModelMetricClaimedVerifiedStatus
1GPT-4Acc30.3Unverified