Chartography
Multimodal · 2026-07-16
Professional graphical-reasoning benchmark testing whether models can interpret domain-native charts such as Kaplan-Meier curves, candlestick charts, contour maps, Sankey diagrams, Bode plots, growth curves, and wind roses.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Mythos 5 | 85.2 |
| Claude Opus 5 | 83.0 |
| Opus 4.8 | 75.0 |
| GPT-5.6 Sol | 45.0 |
| Gemini 3.5 Flash | 35.9 |
| Claude Fable 5 | 34.8 |
| Gemini 3.6 Flash | 34.0 |
| GPT-5.6 Terra | 34.0 |
| GPT-5.6 Luna | 31.4 |
| GPT-5.5 | 31.0 |
| GPT-5.4 | 29.6 |
| Kimi K3 | 26.6 |
| Gemini 3.1 Pro Preview | 26.1 |
| Muse Spark 1.1 | 24.4 |
| Grok 4.5 | 17.3 |
| Sonnet 5 | 16.6 |
| Opus 4.7 | 16.5 |
| Qwen3.5 Plus (2026-02-15) | 15.9 |
| Qwen3.7-Plus | 15.8 |
| Grok 4.3 | 12.9 |
| Kimi K2.5 | 12.6 |
| Kimi K2.6 | 12.2 |
| Gemini 3.5 Flash-Lite | 10.2 |
| Mistral Large 3 675B Instruct 2512 | 9.0 |
| Inkling | 3.4 |