AI Paper Atlas

Research map / Benchmarks / InfoVQA

InfoVQA leaderboard

38 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on InfoVQA. Best accuracy: 88.9 (Agora, ICLR 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

InfoVQA · accuracy

22 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
188.9AgoraWhy Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems
ICLR 2026 · Table 1
LLM agents
287MoCA
Qwen2.5-VL-7B-Instruct
Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
ICML 2026 · Table 1
Multimodal LLMs
386.3AdaThinking-E (ATK)
Qwen3-VL-8B
AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking
ECCV 2026 · Table 1
Reasoning and chain of thought
481.9Manzano-30BMANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
ICLR 2026 · Table 2
Multimodal LLMs
579.1DeFacto
Qwen2.5-VL-7B
DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning
ICML 2026 · Table 2
Multimodal LLMs
679.1OURO-7B
Qwen2-VL-7B-Instruct
OURO: A Self-Bootstrapped Framework for Enhancing Multimodal Scene Understanding
ICCV 2025 · Table 2
Multimodal LLMs
775.9ROSE-7B
Qwen2.5-7B
ROSE: Rotate Your Large Language Model to See
CVPR 2026 · Table 1
Multimodal LLMs
875PVCInternVL2-8B
InternVL2-8B
PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
CVPR 2025 · Table 2
Video-language understanding
966.2Omni-SMoLA PaLI-X FT, per-task LoRA
Omni-SMoLA PaLI-X FT
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts
CVPR 2024 · Table 7
Multimodal LLMs
1064.8OneCAT-3B
Qwen2.5-3B-instruct
OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation
CVPR 2026 · Table understanding 1
Human and embodied modeling
12 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

InfoVQA · score

16 papers, each with its best reported number for its own method; higher is better.

#score ↑MethodPaperTopic
189.3AutoMoT (frozen VLM)
Qwen3-VL-4B
AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture -of-Transformers for End-to-End Autonomous Driving
ICML 2026 · Table 3
Robot action and navigation
281.52HilbertA
Qwen3-VL-8B
HilbertA: Hilbert-Curve–Aligned Sparse Attention for 2D Structured Data
ICML 2026 · Table 4
Attention and transformers
375.2Marten
InternViT-300M + InternLM2 7B
Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding
CVPR 2025 · Table 3
Visual question answering
470.5CLI
LLaVA-OV-7B
From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion
ECCV 2026 · Table 1/2
Multimodal LLMs
570UniARUnified Multimodal Autoregressive Modeling with Shared Context—Visual Tokenizer is Key to Unification
ICML 2026 · Table 4
Human and embodied modeling
669.34KHD with newline token
InternLM2-7B
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
NeurIPS 2024 · Table: Influence of Indicator
Multimodal LLMs
758.5MM1.5-3B
MM1-3B
MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
ICLR 2025 · Table: Text-rich Benchmarks
Multimodal LLMs
856NaViL-2B
InternLM2-1.8B
NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
NeurIPS 2025 · Table: Comparison with existin
Multimodal LLMs
955.7HiRes-LLaVA
Llama3.1-Ins-8B
HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models
CVPR 2025 · Table: Quantitative results on
Multimodal LLMs
1047.4UDOP
T5-large
Unifying Vision, Text, and Layout for Universal Document Processing
CVPR 2023 · Table: Comparison with existin
Human and embodied modeling
6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.