PolyChartQA (CoT): leaderboard

Question answering over multi-chart images on PolyChartQA (2026, Beyond Single Plots): 519 human-written questions about figures that combine several related charts from computer science papers, answered with chain-of-thought prompting. Accuracy in percent rated by human evaluators; higher is better.

Metric: H-Accuracy (%, times 100), chain-of-thought prompting, on the 519 human-authored questions of PolyChartQA (534 multi-chart images with 2,297 sub-charts from computer science papers), answers rated correct by human evaluation (H-Accuracy); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.0 Flash71.87#723
2Claude 3.7 Sonnet66.09#470
3GPT-4.159.54#505
4Pixtral-12B53.76#2553
5ChartGemma23.51#8644
6Gemma 3 4B (IT)22.74#4139
7LLaVA-v1.5-7B11.75#7630
8Llama 3.2 11B Vision8.09#4264
9MatCha6.17

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=polychartqa-cot · How It Works · Data refreshed daily, snapshot 2026-11-21.