AI Paper Atlas

Research map / Benchmarks / VideoMMMU

VideoMMMU leaderboard

23 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VideoMMMU. Best accuracy: 68.1 (SAGE-Flash (SFT+RL), 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.

VideoMMMU · accuracy

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

#accuracy ↑MethodPaperTopic
168.1SAGE-Flash (SFT+RL)
Qwen3-VL-8B
SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning
CVPR 2026 · Table (Video-MMMU)
Video-language understanding
266.2OneThinker-8B
Qwen3-VL-8B-Instruct
OneThinker: All-in-one Reasoning Model for Image and Video
CVPR 2026 · Table 2
Multimodal LLMs
365VideoAuto-R1
Qwen3-VL-8B
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
CVPR 2026 · text
Video-language understanding
464.56DeltaVid-Qwen3-VL-8B
Qwen3-VL-8B
DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences
NeurIPS 2026 · Table 2
Video-language understanding
562.7HippoVLM-8B (64 frames)
Qwen3-8B
Enhancing Video Vision Language Model with Hippocampal Sensing
CVPR 2026 · Table 1
Video-language understanding
656.9Video-FLAIR
Qwen2.5-VL-7B
Video-FLAIR: Not Whether to Reason, But How
NeurIPS 2026 · Table 2
Video-language understanding
754.9VideoRFT + FFR
VideoRFT-SFT 7B
Find, Fix, Reason: Context Repair for Video Reasoning
ICML 2026 · Table 2
Reasoning and chain of thought
854.2VITAL-7B
Qwen2.5-VL-7B
Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning
CVPR 2026 · Table 3
Video-language understanding
954.2RLER
Qwen2.5-VL-7B
Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning
CVPR 2026 · Table 1
Video-language understanding
1053.1Video-KTR
Qwen2.5-VL-7B (64 frames)
Video-KTR: Reinforcing Video Reasoning via Key Token Attribution
ICLR 2026 · Table 1
Video-language understanding
13 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.