Kaggle Prompt to Product: leaderboard

Browser-tested full-stack web application benchmark on Kaggle (shashcoder/prompt-to-product) evaluating models across three tasks (StudySprint, ShopFront, DataDash) on functionality, data accuracy, persistence, responsiveness, accessibility, security, and visual design. Reports Kaggle's unweighted mean score (0-100) over complete numeric rows.

Metric: Mean browser-tested web app score (0-100). Source: www.kaggle.com. Saturation forecast: Estimated already saturated. 39 models tracked. Updated 21 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-5.6 Sol98.17#37
2Gemini 4 Argon98.17#19
3Claude Sonnet 5.598.17#24
4GPT-5.598#54
5Claude Haiku 5.598#75
6GPT-6 Luna97.5#105
7Gemini 3 Flash (Preview)97.33#152
8GPT-6.1 Sol96.33#15
9Gemma 4 31B96.17#382
10Gemini 3.6 Flash95.5#81
11Claude Opus 4.795#85
12Gemini 3.1 Pro (Preview)94.83#99
13Claude Opus 4.694.67#113
14Claude Opus 4.594.5#160
15GPT-6 Sol94.17#34

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

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