AI Paper Atlas

Research map / Benchmarks / RealWorldQA

RealWorldQA leaderboard

70 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on RealWorldQA. Best accuracy: 80.2 (L2-VMAS, ICML 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.

RealWorldQA · accuracy

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

#accuracy ↑MethodPaperTopic
180.2L2-VMAS
Qwen3-VL-8B-Thinking
Dual Latent Memory for Visual Multi-agent System
ICML 2026 · Table 1
LLM agents
276.1DREAM-R
Target Qwen3-VL-32B, draft Qwen3-VL-2B
DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution
ICML 2026 · Table 2
Reasoning and chain of thought
375.6MMFineReason-8B (SFT+RL)
Qwen3-VL-8B-Instruct
MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
NeurIPS 2026 · Table 3
Multimodal LLMs
475.2Molmo-72B
Qwen2 72B
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
CVPR 2025 · Table 1
Multimodal LLMs
574.51Staged training
Qwen3-VL-8B
From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
ICML 2026 · Table 2
Multimodal LLMs
674.5AIF
Qwen2.5-VL-7B
Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow
CVPR 2026 · Table 2
Multimodal LLMs
773.1Bee-8B-RL
Qwen3-8B
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
ICLR 2026 · Table 2
Multimodal LLMs
872.55Self-Consistency
Qwen3-VL-4B
On Test-Time Scaling for Vision-Language Models
ECCV 2026 · Table 1
Multimodal LLMs
971.9CogSense-8B
Qwen3-VL-8B
Toward Cognitive Supersensing in Multimodal Large Language Models
NeurIPS 2026 · Table 2
Multimodal LLMs
1071.83Ours (counting SFT + focus + head temperature)
Qwen3-VL-8B
Learning from Primitive: Probing Visual Reasoning of LVLMs via Counting
ECCV 2026 · Table 3
Multimodal LLMs
47 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

RealWorldQA · score

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

#score ↑MethodPaperTopic
174.9Qwen2-VL-7B+Critic-V
Qwen2-VL-7B
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
CVPR 2025 · Main results table
Multimodal LLMs
274.6DenseMLLM
DenseMLLM-4B
DenseMLLM: Standard Multimodal LLMs for Dense Prediction
ICML 2026 · Table 2
Multimodal LLMs
368.5UniARUnified Multimodal Autoregressive Modeling with Shared Context—Visual Tokenizer is Key to Unification
ICML 2026 · Table 4
Human and embodied modeling
468.5VisionThink
Qwen2.5-VL-7B-Instruct
VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
NeurIPS 2025 · Table: Effective Performance C
Multimodal LLMs
567.32AdaptVision
Qwen2.5-VL-7B-Instruct
AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
CVPR 2026 · Table 1
Multimodal LLMs
665.5Qwen2.5-VL +Cold Start +Multimodal RL
Qwen2.5-VL
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
NeurIPS 2025 · Perception benchmark table
Multimodal LLMs
764.3HaploVL-7B-Pro
Qwen2.5-7B
HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding
ICML 2025 · Main results table
Language, safety and interpretability
863.9SAIL
Mistral-7B-v0.1
The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer
ICCV 2025 · Table 2
Cross-modal learning
962.4EVEv2.0 (Ours)
Qwen2.5-7B
EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
ICCV 2025 · Table 2 (main comparison)
Multimodal LLMs
1062EvoTok (Ours)
Qwen-2.5-7B-Instruct
EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation
ECCV 2026 · Table 2
Autoregressive and latent generation
3 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.