SOTAVerified

Visual Reasoning

Ability to understand actions and reasoning associated with any visual images

Papers

Showing 110 of 698 papers

TitleStatusHype
LaViPlan : Language-Guided Visual Path Planning with RLVR0
Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual ReasoningCode0
PyVision: Agentic Vision with Dynamic Tooling0
MagiC: Evaluating Multimodal Cognition Toward Grounded Visual Reasoning0
Orchestrator-Agent Trust: A Modular Agentic AI Visual Classification System with Trust-Aware Orchestration and RAG-Based ReasoningCode0
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement LearningCode2
Skywork-R1V3 Technical ReportCode7
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning0
Foundation Models for Zero-Shot Segmentation of Scientific Images without AI-Ready Data0
MiCo: Multi-image Contrast for Reinforcement Visual Reasoning0
Show:102550
← PrevPage 1 of 70Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GPT-4o + CAText Score75.5Unverified
2GPT-4V (CoT, pick b/w two options)Text Score75.25Unverified
3GPT-4V (pick b/w two options)Text Score69.25Unverified
4MMICL + CoCoTText Score64.25Unverified
5GPT-4V + CoCoTText Score58.5Unverified
6OpenFlamingo + CoCoTText Score58.25Unverified
7GPT-4VText Score54.5Unverified
8FIBER (EqSim)Text Score51.5Unverified
9FIBER (finetuned, Flickr30k)Text Score51.25Unverified
10MMICL + CCoTText Score51Unverified