SOTAVerified

Chart Question Answering

Question Answering task on charts images

Papers

Showing 125 of 50 papers

TitleStatusHype
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and BeyondCode5
Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction TuningCode2
ScreenAI: A Vision-Language Model for UI and Infographics UnderstandingCode2
StructChart: On the Schema, Metric, and Augmentation for Visual Chart UnderstandingCode2
Pix2Struct: Screenshot Parsing as Pretraining for Visual Language UnderstandingCode2
ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical ReasoningCode2
ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question AnsweringCode1
RefChartQA: Grounding Visual Answer on Chart Images through Instruction TuningCode1
VProChart: Answering Chart Question through Visual Perception Alignment Agent and Programmatic Solution ReasoningCode1
SIMPLOT: Enhancing Chart Question Answering by Distilling EssentialsCode1
PaLI-3 Vision Language Models: Smaller, Faster, StrongerCode1
PaLI-X: On Scaling up a Multilingual Vision and Language ModelCode1
UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and ReasoningCode1
Classification-Regression for Chart ComprehensionCode1
ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering0
ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering0
ChartCards: A Chart-Metadata Generation Framework for Multi-Task Chart UnderstandingCode0
ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models0
Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?Code0
DomainCQA: Crafting Expert-Level QA from Domain-Specific Charts0
Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering0
ChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution0
SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized ImagesCode0
RealCQA-V2 : Visual Premise Proving A Manual COT Dataset for Charts0
ChartKG: A Knowledge-Graph-Based Representation for Chart Images0
Show:102550
← PrevPage 1 of 2Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ChartPaLI-5B + PaLM 2-S1:1 Accuracy81.3Unverified
2Gemini Ultra1:1 Accuracy80.8Unverified
3DePlot+FlanPaLM+Codex (PoT Self-Consistency)1:1 Accuracy79.3Unverified
4ChartPaLI-5B1:1 Accuracy77.3Unverified
5DePlot+Codex (PoT Self-Consistency)1:1 Accuracy76.7Unverified
6ScreenAI 5B (4.62 B params, w/ OCR)1:1 Accuracy76.7Unverified
7SMoLA-PaLI-X Specialist Model1:1 Accuracy74.6Unverified
8SMoLA-PaLI-X Generalist Model1:1 Accuracy73.8Unverified
9MatCha4096 + LaMenDa1:1 Accuracy72.64Unverified
10PaLI-X (Single-task FT w/ OCR)1:1 Accuracy72.3Unverified
#ModelMetricClaimedVerifiedStatus
1MatCha4096 + LaMenDa1:1 Accuracy92.89Unverified
2MatCha1:1 Accuracy91.5Unverified
3DePlot+FlanPaLM+Codex (PoT Self-Consistency)1:1 Accuracy66.6Unverified
4VL-T5-OCR1:1 Accuracy66Unverified
5CRCT1:1 Accuracy55.7Unverified
6VisionTapas-OCR1:1 Accuracy53.9Unverified
#ModelMetricClaimedVerifiedStatus
1vlt5 - 11th ep FineTune1:1 Accuracy0.31Unverified
2Matcha-chartQA1:1 Accuracy0.26Unverified
3crct- 11th ep FineTune1:1 Accuracy0.24Unverified
4vlt5 - baseline1:1 Accuracy0.19Unverified
5crct - baseline1:1 Accuracy0.18Unverified