ChartArena - Flowchart (English): leaderboard
Metric: mAP-high (%) on English flowcharts, 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: Around December 2026. 40 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 65.6 |
| 2 | Seed 2.0 Pro (Non-reasoning) | 62.6 |
| 3 | Qwen 3.5 35B A3B (Thinking) | 62.5 |
| 4 | Gemini 2.5 Pro | 62.1 |
| 5 | Kimi K2.5 (Non-reasoning) | 59.9 |
| 6 | Gemma 4 31B (IT) | 59.6 |
| 7 | GPT-5 | 58.1 |
| 8 | Qwen 3 VL 235B A22B Instruct | 57.9 |
| 9 | MiMo-V2-Omni | 57.1 |
| 10 | Qwen 2.5 VL 72B Instruct | 50.1 |
| 11 | Qwen 3 VL 8B Instruct | 50 |
| 12 | GPT-4o | 49.8 |
| 13 | Qwen 3 VL 8B (Thinking) | 45.7 |
| 14 | Qwen 3.5 9B | 45.5 |
| 15 | Qwen 3 VL 4B Instruct | 44.7 |
Interactive version: theaggregate.ai/benchmark?slug=chartarena-flowchart-english · How It Works · Data refreshed daily, snapshot 2026-09-29.