Do VLMs Truly "Read" Candlesticks? A Multi-Scale Benchmark for Visual Stock Price Forecasting

TL;DR

This paper introduces a multi-scale candlestick chart dataset and evaluation framework to assess vision-language models' ability to understand and predict stock prices from visual market signals.

Contribution

It creates a new multi-scale dataset and standardized evaluation method to systematically benchmark VLMs' comprehension of complex visual stock data.

Findings

Most VLMs perform well only in persistent trend conditions.

VLMs show limited sensitivity to forecast horizons and explicit temporal cues.

Significant prediction biases and weak performance in typical market scenarios.

Abstract

Vision-language models(VLMs) are increasingly applied to visual stock price forecasting, yet existing benchmarks inadequately evaluate their understanding of stock price in candlestick charts. First, prior studies fail to isolate VLMs' comprehension of visual inputs genuinely improves predictive performance and whether VLMs truly comprehend candlestick patterns. Further, most existing datasets and evaluation setups are designed around single-period or tabular inputs. However, human analysts strongly rely on multi-scale candlestick charts, where longer-term horizons capture trend direction and shorter-term horizons provide cues for inflection points, making it difficult to systematically assess VLMs' ability to integrate short-term and long-term visual market dynamics. To bridge this gap, we construct a multi-scale candlestick charts dataset and a standardized evaluation framework to assess VLMs' ability to utilize multi-scale visual market signals. Evaluation combines confusion-matrix-based diagnostics with information coefficient(IC) time series metrics and includes XGBoost as a feature-based temporal baseline. Using this dataset, we benchmark representative VLMs and analyze their ability to leverage multi-scale stock price data. Experimental results show that most VLMs perform well only under persistent uptrend or downtrend conditions, while exhibiting weak predictive capability in more common market scenarios. We also identify significant prediction biases and limited sensitivity to explicitly specified forecast horizons in prompts, indicating inherent limitations in precise temporal reasoning.