AI Paper Atlas

Research map / Benchmarks / MMVU

MMVU leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MMVU. Best accuracy: 73.1 (ADPO, NeurIPS 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.

MMVU · accuracy

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

#accuracy ↑MethodPaperTopic
173.1ADPO
Qwen3-VL-8B
Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
NeurIPS 2026 · Table 3
Multimodal LLMs
270.1VideoRFT + FFR
VideoRFT-SFT 7B
Find, Fix, Reason: Context Repair for Video Reasoning
ICML 2026 · Table 2
Reasoning and chain of thought
369.7VideoAuto-R1
Qwen2.5-VL-7B
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
CVPR 2026 · Table 3
Video-language understanding
468.6ParaVT-8B
Qwen3-VL-8B
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
NeurIPS 2026 · Table 1
Video-language understanding
568.6SDRL (Ours)
Qwen2.5-VL-7B
Reinforcing Structured Chain-of-Thought for Video Understanding
CVPR 2026 · Table 2
Reasoning and chain of thought
667.2Video-o3 (SFT+RL)
Qwen2.5-VL-7B
Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning
ICML 2026 · Table 1
Video-language understanding
765.6Ours
Qwen-VL-2.5-7B
Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization
AAAI 2026 · Table 1
Multimodal LLMs
865.6+ AVATAR
Qwen2.5-Omni-7B
AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video
CVPR 2026 · Table 2
Video-language understanding
965.4DeltaVid-Qwen3-VL-8B
Qwen3-VL-8B
DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences
NeurIPS 2026 · Table 2
Video-language understanding
1061.3Qwen-2.5VL-7B + Combined
Qwen-2.5VL-7B
VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
NeurIPS 2025 · Table: Post-training performan
Multimodal LLMs
2 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.