AI Paper Atlas

Research map / Benchmarks / MMMU-Pro

MMMU-Pro leaderboard

18 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MMMU-Pro. Best accuracy: 55.5 (Unsupervised ICL, ICLR 2025).

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.

MMMU-Pro · accuracy

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

#accuracy ↑MethodPaperTopic
155.5Unsupervised ICL
GPT-4o
Large (Vision) Language Models are Unsupervised In-Context Learners
ICLR 2025 · GPT-4o results table
CLIP and zero-shot
254.8ARES-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
353.1ProxyThinker (expert VL-Rethinker-7B)
Qwen2.5-VL-72B
ProxyThinker: Test-Time Guidance through Small Visual Reasoners
ICLR 2026 · Table 1
Multimodal LLMs
451.3SRPO-32B
Qwen2.5-VL-32B-Instruct
SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
NeurIPS 2025 · Table 1
Reasoning and chain of thought
549.69CAR-7B
Qwen2.5-VL-7B
Context-Aware Reasoner: Enhancing Contextual Reasoning in Multimodal Large Language Models
ICML 2026 · Table 3
Multimodal LLMs
644.7PTA-GRPO
Qwen2.5-7B-VL
Plan Then Action: High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
ICML 2026 · Table 5
Reasoning and chain of thought
742.9AVAR-Thinker
Qwen2.5-VL-7B
From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
ICLR 2026 · Table 1
Multimodal LLMs
842.9OpenVLThinker-7B
Qwen2.5-VL-7B
OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
NeurIPS 2025 · Main results table
Multimodal LLMs
942.5PDCR
Qwen2.5-VL-7B
PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
CVPR 2026 · Table 1
Multimodal LLMs
1041.2Vision-G1
Qwen2.5-VL-7B
Vision-G1: Towards General Reasoning Vision-Language Models via Reinforcement Learning
AAAI 2026 · Table 1
Multimodal LLMs
8 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.