ExChart-Bench - Pie Charts: leaderboard
Metric: Adaptive MAPE (%; 3,055 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
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 | 4.59 |
| 2 | GLM-4.5V | 9.24 |
| 3 | Qwen 2.5 VL 72B Instruct | 10.45 |
| 4 | GPT-4o | 11.35 |
| 5 | Gemini 2.5 Flash | 11.58 |
| 6 | Qwen 2.5 VL 32B Instruct | 11.76 |
| 7 | Qwen 2.5 VL 7B Instruct | 14.64 |
Interactive version: theaggregate.ai/benchmark?slug=exchart-bench-pie-charts · How It Works · Data refreshed daily, snapshot 2026-09-25.