AI Paper Atlas

Research map / Benchmarks / MathVista (testmini)

MathVista (testmini) leaderboard

15 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MathVista (testmini). Best accuracy: 83.1 (Look-Back + VisRef, CVPR 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.

MathVista (testmini) · accuracy

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

#accuracy ↑MethodPaperTopic
183.1Look-Back + VisRef
InternVL3.5-8B
VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models
CVPR 2026 · Table 2
Multimodal LLMs
281.74Qwen-8B-DeltaThinker
Qwen3-VL-8B-Thinking
DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
NeurIPS 2026 · Table 3
Knowledge distillation
379.7ThinkLite-VL-72B
Qwen2.5-VL-72B-Instruct
SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
NeurIPS 2025 · Table: Comparison of different
Multimodal LLMs
479.5OMR-7B
Qwen2.5-VL-7B-Instruct
OpenMMReasoner: Pushing the Frontiers in Multimodal Reasoning with an Open and General Recipe
CVPR 2026 · Table (main results)
Multimodal LLMs
578.1ProxyThinker (expert VL-Rethinker-7B)
Qwen2.5-VL-32B
ProxyThinker: Test-Time Guidance through Small Visual Reasoners
ICLR 2026 · Table 1
Multimodal LLMs
674.4AdaVaR-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
774.2Perception-R1-7B
Qwen2.5-VL-7B-IT
Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward
ICLR 2026 · Table 1
Multimodal LLMs
873.3Manzano-30BMANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
ICLR 2026 · Table 2
Multimodal LLMs
971.6ViSurf
Qwen2.5-VL-7B
ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models
ICML 2026 · Table 1
Multimodal LLMs
1071.3SophiaVL-R1-7B
Qwen2.5-VL-7B-Instruct
SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
ICLR 2026 · Table 1
Reasoning and chain of thought
5 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.