OpenCodePapers
video-question-answering-on-tomato
Video Question Answering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
Accuracy
↕
ModelName
ReleaseDate
↕
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
✓ Link
40.3
V-JEPA 2 ViT-g (1B, 384px) + Llama 3.1 (8B)
2025-06-11
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
✓ Link
39.8
Molmo2-4B
2026-01-15
MOSS-VL Technical Report
✓ Link
39.5
MOSS-VL-Instruct-0708
2026-08-15
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
✓ Link
37.9
VideoChat3-4B
2026-07-16
InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning
✓ Link
37.4
InternVideo3-8B
2026-06-10
Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
✓ Link
36.5
Molmo2 (SigLIP2 So400M + Qwen3-4B) baseline
2026-03-18
MotionAtlas: A High-Quality Dataset and Benchmark for Dense Motion Captioning
✓ Link
35.2
MotionAtlas-4B
2026-09-08
EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning
✓ Link
34.5
EgoVITA (Qwen3-VL)
2025-11-23
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
✓ Link
33.2
PLM-8B
2025-04-17
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
✓ Link
32.6
DNA-Train-7B
2025-12-30
Kimi-VL Technical Report
✓ Link
31.7
Kimi-VL-A3B-Instruct
2025-04-10
CoPE-VideoLM: Codec Primitives For Efficient Video Language Models
28.3
CoPE 7B
2026-02-13
Incentivizing Versatile Video Reasoning in MLLMs via Data-Efficient Reinforcement Learning
✓ Link
27.8
VideoReasoner (Qwen2-VL-7B-Base + RL)
2026-06-03
×