AI Paper Atlas

Research map / Benchmarks / VideoMME Long

VideoMME Long leaderboard

26 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VideoMME Long. Best accuracy: 78.1 (Symphony, 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.

VideoMME Long · accuracy

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

#accuracy ↑MethodPaperTopic
178.1Symphony
DeepSeek R1 + Seed 1.6 VL
Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understanding
CVPR 2026 · Table 2
Video-language understanding
277.7MERIT
GPT-5
Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding
ECCV 2026 · Table 2
Video-language understanding
376.6WorldMM-GPT
GPT-5
WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
CVPR 2026 · Table 1
Video-language understanding
472.2Qwen2-VL + ViG-RAG
Qwen2-VL 72B
ViG-RAG: Video-aware Graph Retrieval-Augmented Generation via Temporal and Semantic Hybrid Reasoning
AAAI 2026 · Table 2
Video-language understanding
570LensWalk (o3/GPT-4.1) full
o3 reasoner, GPT-4.1 observer
LensWalk: Agentic Video Understanding by Planning How You See in Videos
CVPR 2026 · Table 4
Video-language understanding
664.9Ego-R1
Qwen2.5-3B-Instruct
Ego-R1: Agentic Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
TPAMI 2026 · Table 2
Video-language understanding
764Prism
Qwen3-VL-8B
Prism: Spectral-Aware Block-Sparse Attention
ICML 2026 · Table 3
Attention and transformers
863.2LLaVA-Next-Video + XComp
LLaVA-Next-Video
One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
NeurIPS 2025 · Table: Generalize to LLaVA-Nex
Video-language understanding
962.7Qwen3-VL + CLEAR
Qwen3-VL-8B
Diagnosing and Correcting Bias in MLLM for Long Video Understanding
NeurIPS 2026 · Table 1
Video-language understanding
1061.8M3-AgentSeeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
ICLR 2026 · Table 1
LLM agents
16 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.