OpenCodePapers

video-question-answering-on-videoholmes

Video Question Answering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning74.6OmniSeek (ours)2026-10-01
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs✓ Link65.5Video-ORA-9B2026-08-20
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction✓ Link64.3MiniCPM-o 4.5-Instruct2026-04-30
Omni-Streaming Thinking✓ Link60.0OST2026-09-14
EventLens: Event-Structure Reinforcement Learning for Video Understanding✓ Link59.44EventLens-8B2026-10-12
Training-Free Speech-Centric Omni Understanding with Frozen VLMs✓ Link59.3MiniCPM4.5-V-TFO-9B2026-08-07
AdaTooler-V: Adaptive Tool-Use for Images and Videos✓ Link58.3AdaTooler-V-7B2025-12-18
Qwen3-Omni Technical Report✓ Link57.3Qwen3-Omni-Flash-Thinking2025-09-22
OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering✓ Link52.53OmniJigsaw (CMM)2026-04-09
OneThinker: All-in-one Reasoning Model for Image and Video✓ Link48.7OneThinker-8B2025-12-02
Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence✓ Link48.0Open-o3-Video-v2-4B2026-10-13
Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation47.07Qwen2.5-Omni-3B (Stage 2: Mixed-Modality RLVR)2026-05-13
VAST: Video Ability-Stratified Taxonomy for Data-Efficient Video Reasoning42.5VideoVAST-7B (extra data)2026-06-03
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously✓ Link41.9VST-7B2026-03-12
Rethinking Chain-of-Thought Reasoning for Videos✓ Link41.6Qwen2.5-VL-7B (GRPO, concise reason, trained with token compression & 6x frames)2025-12-10
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models40.2Insight-V++2026-03-18
EVA: Efficient Reinforcement Learning for End-to-End Video Agent✓ Link36.7EVA (GRPO)2026-03-24