AI Paper Atlas

Research map / Benchmarks / NExT-QA

NExT-QA leaderboard

42 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on NExT-QA. Best accuracy: 86.8 (PPLLaVA, ICLR 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.

NExT-QA · accuracy

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

#accuracy ↑MethodPaperTopic
186.8PPLLaVA
InternVL3
PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
ICLR 2026 · Table 2
Video-language understanding
284.3Qwen2.5-VL-72B + ReAgent-V
Qwen2.5-VL-72B
ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding
NeurIPS 2025 · Table 1
Video-language understanding
384.2ReMoRa
Qwen2-7B
ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding
CVPR 2026 · Table 1
Video-language understanding
484.2AdaCodec (comparable token budget)
Qwen3-VL-8B
AdaCodec: A Predictive Visual Code for Video MLLMs
NeurIPS 2026 · Table 1
Video-language understanding
584.1F-16-7B
LLaVA-OneVision 7B
Improving LLM Video Understanding with 16 Frames Per Second
ICML 2025 · Table 1
Video-language understanding
684TallVA-8B-A7B
Qwen2-7B
Task-Aware Mechanism: Hybrid MoE Vision Tower Towards Holistic Video Understanding
ICML 2026 · Table 1
Video-language understanding
784Flow4Agent
LLaVA-Video-7B
Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow
ICCV 2025 · Table 1
Video-language understanding
883.9LLaVA-Video + QuoTA
LLaVA-Video-7B
QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension
AAAI 2026 · Table 2
Video-language understanding
983.8LLaVA-Video-7B + ST-GridPool
LLaVA-Video-7B
Enhancing Visual Token Representations for Video Large Language Models via Training-free Spatial-Temporal Pooling and Gridding
ICLR 2026 · Table 1
Video-language understanding
1083.73BIMBA-LLaVA
Qwen2-7B
BIMBA: Selective-Scan Compression for Long-Range Video Question Answering
CVPR 2025 · Table 3
Video-language understanding
32 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.