WebApp1K — leaderboard
React web app code generation benchmark: 1,000 single-task problems across 20 scenarios (blogging, ecommerce, weather, etc.) testing functional correctness with pass@1.
Metric: Pass@1 (%). Source: huggingface.co. Status: saturated. 34 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 Mini | 96.1 |
| 2 | O1 Preview | 95.2 |
| 3 | O1 Mini | 93.9 |
| 4 | DeepSeek R1 | 92.7 |
| 5 | GPT-4o (2024-08-06) | 88.5 |
| 6 | Claude 3.5 Sonnet (20240620) | 88.08 |
| 7 | DeepSeek V3 | 87.23 |
| 8 | GPT-4o (2024-05-13) | 87.02 |
| 9 | QwQ-32B | 87 |
| 10 | Gemini 2.0 Flash (Thinking) | 85.9 |
| 11 | DeepSeek V2.5 | 83.38 |
| 12 | GPT-4o Mini | 82.71 |
| 13 | Gemini 2.0 Flash | 82.2 |
| 14 | Mistral Large 2 (Jul) | 78.04 |
| 15 | Llama 4 Maverick | 76.9 |
Interactive version: theaggregate.ai/benchmark?slug=webapp1k · How the rankings work · Data refreshed daily, snapshot 2026-07-22.