DV-World - DV-Sheet Dashboard: leaderboard
Spreadsheet dashboard creation on DV-World (2026), run in the DV-World-Agent framework: an MLLM judge rubric score for insight, accuracy, professionalism and aesthetics of the finished dashboard. Percent; higher is better.
Metric: Dashboard overall (%): MLLM rubric score (insightfulness, accuracy, professionalism, aesthetics) of the stitched spreadsheet dashboard, 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 February 2027. 11 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-4.7 | 38.03 | #380 |
| 2 | DeepSeek V3.2 | 36.35 | #419 |
| 3 | Gemini 3 Pro (Preview) | 35.29 | #119 |
| 4 | GPT-5.2 | 33.98 | #185 |
| 5 | GPT-4.1 | 32.21 | #505 |
| 6 | Grok 4 | 27.78 | #319 |
| 7 | Gemini 2.5 Pro | 23.6 | #276 |
| 8 | Kimi K2 (Thinking) | 19.37 | |
| 9 | Qwen 3 Coder Plus | 17.73 | #720 |
| 10 | Qwen 3 235B A22B | 17.01 | #628 |
| 11 | Qwen 3 8B | 4.06 | #1873 |
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-sheet-dashboard · How It Works · Data refreshed daily, snapshot 2026-11-21.