ChartArena - Pie Chart (Chinese): leaderboard
Metric: mAP-high (%) on Chinese pie charts, each model parses the chart image into its native structured format, normalized format-agnostically to (header, entity, value) triples for numeric charts or to labeled graphs and trees for flowcharts and mind maps; mean average precision over similarity thresholds at the high tolerance level, averaged over three visual styles (digital renderings, printed photos, hand-drawn photos); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 43 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 95.1 |
| 2 | Seed 2.0 Pro (Non-reasoning) | 90.5 |
| 3 | Qwen 3.5 35B A3B (Thinking) | 88.4 |
| 4 | Gemini 2.5 Pro | 87.3 |
| 5 | Gemma 4 31B (IT) | 87.2 |
| 6 | Kimi K2.5 (Non-reasoning) | 86.7 |
| 7 | MiMo-V2-Omni | 85.8 |
| 8 | Qwen 3 VL 235B A22B Instruct | 85.5 |
| 9 | Qwen 3 VL 4B Instruct | 85.5 |
| 10 | Qwen 3 VL 8B Instruct | 84.7 |
| 11 | Qwen 2.5 VL 32B Instruct | 84.7 |
| 12 | Qwen 3 VL 8B (Thinking) | 84.2 |
| 13 | GLM-4.5V | 83.1 |
| 14 | Qwen 3.5 4B | 79.6 |
| 15 | GPT-5 | 78.9 |
Interactive version: theaggregate.ai/benchmark?slug=chartarena-pie-chart-chinese · How It Works · Data refreshed daily, snapshot 2026-09-29.