SOTAVerified

Visual Question Answering

MLLM Leaderboard

Papers

Showing 16611670 of 2177 papers

TitleStatusHype
Contextual Dropout: An Efficient Sample-Dependent Dropout ModuleCode0
Visual Question Answering: which investigated applications?Code0
Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues0
Learning Compositional Representation for Few-shot Visual Question Answering0
Going Full-TILT Boogie on Document Understanding with Text-Image-Layout TransformerCode1
SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question AnsweringCode1
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsCode1
Unifying Vision-and-Language Tasks via Text GenerationCode1
Answer Questions with Right Image Regions: A Visual Attention Regularization ApproachCode0
An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games0
Show:102550
← PrevPage 167 of 218Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MMCTAgent (GPT-4 + GPT-4V)GPT-4 score74.24Unverified
2Qwen2-VL-72BGPT-4 score74Unverified
3InternVL2.5-78BGPT-4 score72.3Unverified
4GPT-4o +text rationale +IoTGPT-4 score72.2Unverified
5Lyra-ProGPT-4 score71.4Unverified
6GLM-4V-PlusGPT-4 score71.1Unverified
7Phantom-7BGPT-4 score70.8Unverified
8InternVL2.5-38BGPT-4 score68.8Unverified
9InternVL2-26B (SGP, token ratio 64%)GPT-4 score65.6Unverified
10Baichuan-Omni (7B)GPT-4 score65.4Unverified