ChartAct - Dashboard: leaderboard

ChartAct (2026) Dashboard environment: the same interactive charts and questions embedded in generated dashboard pages with other components as distractors, answered by a multimodal agent acting on screenshots. Success rate in percent; higher is better.

Metric: Success rate (%) in the Dashboard Chart environment (the same chart and questions embedded in a generated dashboard 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 February 2027. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Opus 4.783.7#85
2Kimi K2.5Non-reasoning56.6#266
3GPT-5.551.7#54
4Doubao-Seed-2-0-Pro-260215High39.4
5Qwen 3.5 122B A10B31.9#346
6Gemini 3.1 Pro (Preview)Low31#99
7Qwen 3.6 PlusThinking23.8#238
8GLM-4.6V23#710
9Qwen 3.5 35B A3B20.6#492
10Gemma 4 31B (IT)14.9#350
11Qwen 3 VL PlusThinking13.6#512

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=chartact-dashboard · How It Works · Data refreshed daily, snapshot 2026-11-21.