DV-World - DV-Evol Python: leaderboard
Metric: Overall score (%) on the Python DV-Evol tasks (adapt a reference visualization to new data in the target library: Python Matplotlib/Seaborn, Apache ECharts, Vega-Lite, D3.js or Plotly.js); per-task score = 0.5 x MLLM rubric score (integrity, consistency, aesthetics against gold plots) + 0.5 x table coverage of gold values, run in the DV-World-Agent framework (data manipulation, multimodal perception and proactive interaction tools); expert rubrics applied by a Gemini-2.5-Flash judge where rubric-scored, means over evaluation trials; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 60.36 |
| 2 | Gemini 3 Flash | 58.54 |
| 3 | GPT-5.2 | 55.81 |
| 4 | Grok 4 | 53.84 |
| 5 | Gemini 2.5 Pro | 39.21 |
| 6 | GPT-4.1 | 37.53 |
Interactive version: theaggregate.ai/benchmark?slug=dv-world-dv-evol-python · How It Works · Data refreshed daily, snapshot 2026-10-07.