ExChart-Bench - Line Charts: leaderboard

ExChart-Bench (He et al., Zhejiang University, CHI 2026) gives a multimodal model a chart image with its data labels removed and a CSV template with the values masked, and asks it to fill in the numbers. This board covers the 700 basic and grouped line charts (9,494 values). Adaptive MAPE divides each value's absolute error by the chart's largest absolute value and caps it at 100%, and unparsable output or a table of the wrong shape counts as 100% error; lower is better.

Metric: Adaptive MAPE (%; 9,494 values in 700 charts, per-value error relative to the chart's largest absolute value, capped at 100; unparsable or misshapen tables count 100). Source: arxiv.org. Saturation forecast: Estimated already saturated. 12 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Flash4.35#452
2GLM-4.5V5.56#739
3GPT-4.16.43#492
4Qwen 2.5 VL 72B Instruct6.57#845
5Qwen 2.5 VL 32B Instruct8.08#1055
6GPT-4o9.53#741
7Qwen 2.5 VL 7B Instruct22.4#1842

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=exchart-bench-line-charts · How It Works · Data refreshed daily, snapshot 2026-11-12.