Papers with Code · CC BY-SA 4.0

ChartQA

아카이브 평가 27건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
ChartPaLI-5B + PaLM 2-S	1:1 Accuracy 81.3	Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs 2024-03-19	연결 없음
Gemini Ultra	1:1 Accuracy 80.8	Gemini: A Family of Highly Capable Multimodal Models 2023-12-19	코드 1
DePlot+FlanPaLM+Codex (PoT Self-Consistency)	1:1 Accuracy 79.3	DePlot: One-shot visual language reasoning by plot-to-table translation 2022-12-20	코드 1
ChartPaLI-5B	1:1 Accuracy 77.3	Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs 2024-03-19	연결 없음
DePlot+Codex (PoT Self-Consistency)	1:1 Accuracy 76.7	DePlot: One-shot visual language reasoning by plot-to-table translation 2022-12-20	코드 1
ScreenAI 5B (4.62 B params, w/ OCR)	1:1 Accuracy 76.7	ScreenAI: A Vision-Language Model for UI and Infographics Understanding 2024-02-07	코드 1 · 코드 2
SMoLA-PaLI-X Specialist Model	1:1 Accuracy 74.6	Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts 2023-12-01	연결 없음
SMoLA-PaLI-X Generalist Model	1:1 Accuracy 73.8	Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts 2023-12-01	연결 없음
MatCha4096 + LaMenDa	1:1 Accuracy 72.64	Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA 2024-01-01	연결 없음
PaLI-X (Single-task FT w/ OCR)	1:1 Accuracy 72.3	PaLI-X: On Scaling up a Multilingual Vision and Language Model 2023-05-29	코드 1 · 코드 2
PaLI-X (Single-task FT)	1:1 Accuracy 70.9	PaLI-X: On Scaling up a Multilingual Vision and Language Model 2023-05-29	코드 1 · 코드 2
PaLI-X (Multi-task FT)	1:1 Accuracy 70.6	PaLI-X: On Scaling up a Multilingual Vision and Language Model 2023-05-29	코드 1 · 코드 2
DePlot+FlanPaLM (Self-Consistency)	1:1 Accuracy 70.5	DePlot: One-shot visual language reasoning by plot-to-table translation 2022-12-20	코드 1
PaLI-3	1:1 Accuracy 70	PaLI-3 Vision Language Models: Smaller, Faster, Stronger 2023-10-13	코드 1
PaLI-3 (w/ OCR)	1:1 Accuracy 69.5	PaLI-3 Vision Language Models: Smaller, Faster, Stronger 2023-10-13	코드 1
DePlot+FlanPaLM (CoT)	1:1 Accuracy 67.3	DePlot: One-shot visual language reasoning by plot-to-table translation 2022-12-20	코드 1
Qwen-VL-Chat	1:1 Accuracy 66.3	Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond 2023-08-24	코드 1 · 코드 2
UniChart	1:1 Accuracy 66.24	UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning 2023-05-24	코드 1
Qwen-VL	1:1 Accuracy 65.7	Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond 2023-08-24	코드 1 · 코드 2
StructChart+GPT3.5 (STR ChartQA+SimChart9K)	1:1 Accuracy 65.3	StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding 2023-09-20	코드 1 · 코드 2 · 코드 3
MatCha	1:1 Accuracy 64.2	MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering 2022-12-19	코드 1
StructChart+GPT3.5 (STR)	1:1 Accuracy 60.7	StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding 2023-09-20	코드 1 · 코드 2 · 코드 3
Pix2Struct-large	1:1 Accuracy 58.6	Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding 2022-10-07	코드 1 · 코드 2 · 코드 3 · 코드 4
Pix2Struct-base	1:1 Accuracy 56.0	Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding 2022-10-07	코드 1 · 코드 2 · 코드 3 · 코드 4
VisionTapas-OCR	1:1 Accuracy 45.5	ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning 2022-03-19	코드 1
DePlot+GPT3 (Self-Consistency)	1:1 Accuracy 42.3	DePlot: One-shot visual language reasoning by plot-to-table translation 2022-12-20	코드 1
DePlot+GPT3 (CoT)	1:1 Accuracy 36.9	DePlot: One-shot visual language reasoning by plot-to-table translation 2022-12-20	코드 1