AI Paper Atlas

Research map / Benchmarks / MathVision

MathVision leaderboard

63 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MathVision. Best accuracy: 55 (Gemini-2.0-flash + ContextNav, 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.

MathVision · accuracy

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

#accuracy ↑MethodPaperTopic
155Gemini-2.0-flash + ContextNav
Gemini-2.0-flash
ContextNav: Towards Agentic Multimodal In-Context Learning
ICLR 2026 · Table 1
Multimodal LLMs
251.9ARES-7B
Qwen2.5-VL-7B-Instruct
ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
ICLR 2026 · Table 2
Reasoning and chain of thought
348.8ReVisual-R1-7B
Qwen2.5-VL-7B
Revisual-R1: Advancing Multimodal Reasoning From Optimized Cold Start to Staged Reinforcement Learning
ICLR 2026 · Table 2
Multimodal LLMs
444.8PDCR
Qwen2.5-VL-7B
PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
CVPR 2026 · Table 1
Multimodal LLMs
544.74Expert Merging++
Qwen2-VL-7B
Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking
ICLR 2026 · Table 2
Instruction and fine-tuning
644.6+ ReaGEN (4 iter)
Qwen3-VL-4B
ReaGEN: Adaptive Generation of Structured Chains-of-Thought for Efficient Multimodal Reasoning
CVPR 2026 · Table 1
Multimodal LLMs
744.6LASER
Qwen2.5-VL-7B
LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression
ECCV 2026 · Table 1
Multimodal LLMs
843.9AnE-3rd
Qwen2.5-VL-7B-Instruct
AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution
ECCV 2026 · Table 1
Reasoning and chain of thought
943.7RAPID (Qwen3-8B)
Qwen2.5-VL-7B
Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning
ICLR 2026 · Table 1
Multimodal LLMs
1040.8ProxyThinker (expert OpenVLThinker-7B)
Qwen2.5-VL-32B
ProxyThinker: Test-Time Guidance through Small Visual Reasoners
ICLR 2026 · Table 1
Multimodal LLMs
53 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.