DV-World - DV-Evol: leaderboard

Chart adaptation on DV-World (2026), run in the DV-World-Agent framework: the agent adapts a reference visualization to new data in Python, Apache ECharts, Vega-Lite, D3.js or Plotly.js, scored half by an MLLM rubric against gold plots and half by coverage of the gold values. Mean of the five library scores, in percent; higher is better.

Metric: DV-Evol score (%): mean of the five libraries' overall scores on 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 April 2027. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Pro (Preview)51.44#119
2Gemini 3 Flash49.46#175
3Grok 448.81#319
4GPT-4.144.67#505
5GPT-5.243.04#185
6Gemini 2.5 Pro36.63#276
7Qwen 3 VL Plus29.33#512
8Qwen 3 VL 32B24.17#622
9Qwen 3 VL 8B21.05#917

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

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