SOTAVerified

Visual Question Answering

MLLM Leaderboard

Papers

Showing 18011810 of 2177 papers

TitleStatusHype
Visual Question Answering Using Semantic Information from Image Descriptions0
Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision0
Knowledge-Based Visual Question Answering in Videos0
Visual Grounding Methods for VQA are Working for the Wrong Reasons!Code1
An Entropy Clustering Approach for Assessing Visual Question DifficultyCode0
Rephrasing visual questions by specifying the entropy of the answer distribution0
Understanding Knowledge Gaps in Visual Question Answering: Implications for Gap Identification and Testing0
Evaluating Multimodal Representations on Visual Semantic Textual SimilarityCode1
Generating Rationales in Visual Question Answering0
Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal TransformersCode1
Show:102550
← PrevPage 181 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