AI Paper Atlas

Research map / Benchmarks / MathVerse (Vision Only)

MathVerse (Vision Only) leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MathVerse (Vision Only). Best accuracy: 67 (Bee-8B-RL, 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.

MathVerse (Vision Only) · accuracy

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

#accuracy ↑MethodPaperTopic
167Bee-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
252.4MM-Eureka-Qwen-32B + Activation Replay
MM-Eureka-Qwen-32B
Boosting Reasoning in Large Multimodal Models via Activation Replay
CVPR 2026 · Table 2
Multimodal LLMs
348.73SPECS (Ours-7B)
Qwen2.5-VL-7B
SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
ICLR 2026 · Table 2
RL from feedback
447.59+ ReaGEN (4 iter)
Qwen3-VL-4B
ReaGEN: Adaptive Generation of Structured Chains-of-Thought for Efficient Multimodal Reasoning
CVPR 2026 · Table 1
Multimodal LLMs
545.2MathBook-7B
Qwen2.5-VL-7B
We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
ICLR 2026 · Table 1
Multimodal LLMs
643.3LaCoT-Qwen-7B
Qwen2.5-VL-7B
Latent Chain-of-Thought for Visual Reasoning
NeurIPS 2025 · Table: Test accuracy on visual
Reasoning and chain of thought
743AdaVaR-7B
Qwen2.5-VL-7B
Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning
ICLR 2026 · Table 1
Multimodal LLMs
840R1-Onevision-7B
Qwen2.5-VL-7B
R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
ICCV 2025 · Table 1
Multimodal LLMs
939.1Thyme-VL-7B
Qwen2.5-VL-7B
Thyme: Think Beyond Images
ICLR 2026 · Table 1
Multimodal LLMs
1017.4+Dart-prop
LLaVA-Next-LLaMA3-8B
Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
ICML 2025 · Table 1
Multimodal LLMs

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