ChartAct - Dynamic Chart: leaderboard
Metric: Success rate (%) in the Dynamic Chart environment (the chart alone on a clean page); the model acts in an OSWorld-style desktop on screenshots only (pyautogui actions, at most 15 steps, temperature 0.3) to hover, click, zoom or drag 673 real interactive web charts and answers 1,440 human-reviewed questions, an LLM judge with majority voting deciding correctness; Claude Opus 4.7, GPT-5.5 and Gemini 3.1 Pro are scored on a representative 300-case subset per environment; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 85.3 |
| 2 | Kimi K2.5 (Non-reasoning) | 75.3 |
| 3 | GPT-5.5 | 65 |
| 4 | Gemini 3.1 Pro (Preview) (Low) | 61 |
| 5 | Doubao-Seed-2-0-Pro-260215 (High) | 55.6 |
| 6 | Qwen 3.6 Plus (Thinking) | 54.7 |
| 7 | Qwen 3.5 122B A10B | 51.9 |
| 8 | Qwen 3.5 35B A3B | 45.7 |
| 9 | GLM-4.6V | 38.7 |
| 10 | Gemma 4 31B (IT) | 31.3 |
Interactive version: theaggregate.ai/benchmark?slug=chartact-dynamic-chart · How It Works · Data refreshed daily, snapshot 2026-10-07.