SOTAVerified|Agents Browse Leaderboard About

Chart Question Answering

Question Answering task on charts images

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 31–40 of 50 papers

Title	Date	Tasks	Status	Hype
Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMs	Jun 1, 2024	Chart Question AnsweringChart Understanding	—Unverified	0
ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering	May 11, 2024	Chart Question AnsweringQuestion Answering	—Unverified	0
mChartQA: A universal benchmark for multimodal Chart Question Answer based on Vision-Language Alignment and Reasoning	Apr 2, 2024	Chart Question AnsweringLanguage Modeling	—Unverified	0
Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA	Mar 25, 2024	Chart Question AnsweringData Augmentation	—Unverified	0
Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs	Mar 19, 2024	Chart Question AnsweringOptical Character Recognition (OCR)	—Unverified	0
Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA	Jan 1, 2024	Chart Question AnsweringData Augmentation	—Unverified	0
Do LLMs Work on Charts? Designing Few-Shot Prompts for Chart Question Answering and Summarization	Dec 17, 2023	Chart Question AnsweringQuestion Answering	—Unverified	0
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts	Dec 1, 2023	Chart Question AnsweringDocument AI	—Unverified	0
DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding	Oct 29, 2023	Answer GenerationChart Question Answering	CodeCode Available	0
RealCQA: Scientific Chart Question Answering as a Test-bed for First-Order Logic	Aug 3, 2023	Chart Question AnsweringFormal Logic	CodeCode Available	0

Show:10 25 50

← PrevPage 4 of 5Next →

All datasets ChartQA PlotQA RealCQA

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ChartPaLI-5B + PaLM 2-S	1:1 Accuracy	81.3	—	Unverified
2	Gemini Ultra	1:1 Accuracy	80.8	—	Unverified
3	DePlot+FlanPaLM+Codex (PoT Self-Consistency)	1:1 Accuracy	79.3	—	Unverified
4	ChartPaLI-5B	1:1 Accuracy	77.3	—	Unverified
5	DePlot+Codex (PoT Self-Consistency)	1:1 Accuracy	76.7	—	Unverified
6	ScreenAI 5B (4.62 B params, w/ OCR)	1:1 Accuracy	76.7	—	Unverified
7	SMoLA-PaLI-X Specialist Model	1:1 Accuracy	74.6	—	Unverified
8	SMoLA-PaLI-X Generalist Model	1:1 Accuracy	73.8	—	Unverified
9	MatCha4096 + LaMenDa	1:1 Accuracy	72.64	—	Unverified
10	PaLI-X (Single-task FT w/ OCR)	1:1 Accuracy	72.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MatCha4096 + LaMenDa	1:1 Accuracy	92.89	—	Unverified
2	MatCha	1:1 Accuracy	91.5	—	Unverified
3	DePlot+FlanPaLM+Codex (PoT Self-Consistency)	1:1 Accuracy	66.6	—	Unverified
4	VL-T5-OCR	1:1 Accuracy	66	—	Unverified
5	CRCT	1:1 Accuracy	55.7	—	Unverified
6	VisionTapas-OCR	1:1 Accuracy	53.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	vlt5 - 11th ep FineTune	1:1 Accuracy	0.31	—	Unverified
2	Matcha-chartQA	1:1 Accuracy	0.26	—	Unverified
3	crct- 11th ep FineTune	1:1 Accuracy	0.24	—	Unverified
4	vlt5 - baseline	1:1 Accuracy	0.19	—	Unverified
5	crct - baseline	1:1 Accuracy	0.18	—	Unverified