ChartArena - Combination Chart (Chinese): leaderboard
ChartArena (2026) tests chart parsing: a model converts a chart image into structured data, scored format-agnostically as triples for numeric charts or as labeled graphs and trees for flowcharts and mind maps. This board is mAP at the high tolerance level in percent on Chinese combination charts, averaged over digital, printed-photo and hand-drawn styles; higher is better.
Metric: mAP-high (%) on Chinese combination 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: Around February 2027. 43 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 70.3 | #94 |
| 2 | Kimi K2.5 (Non-reasoning) | 63.6 | #256 (Kimi K2.5) |
| 3 | Gemma 4 31B (IT) | 59.3 | #342 |
| 4 | Qwen 3 VL 235B A22B Instruct | 58.2 | #522 |
| 5 | Gemini 2.5 Pro | 57.6 | #266 |
| 6 | Qwen 3.5 35B A3B (Thinking) | 56.9 | #482 (Qwen 3.5 35B A3B) |
| 7 | GLM-4.5V | 52.5 | #744 |
| 8 | Qwen 2.5 VL 72B Instruct | 50.5 | #846 |
| 9 | Qwen 3.5 9B | 49.5 | #803 |
| 10 | Qwen 3 VL 8B Instruct | 47.9 | #981 |
| 11 | Qwen 2.5 VL 32B Instruct | 47.3 | #1053 |
| 12 | Qwen 3 VL 4B Instruct | 47.1 | #1279 |
| 13 | Qwen 3.5 4B | 46.7 | #1175 |
| 14 | GPT-5 | 46.5 | #167 |
| 15 | Qwen 3 VL 8B (Thinking) | 46.2 | #887 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=chartarena-combination-chart-chinese · How It Works · Data refreshed daily, snapshot 2026-11-13.