WebApp1K-React: leaderboard
WebApp1K benchmark measuring whether models generate correct, test-passing React web-application code from feature specs.
Metric: pass@1. Source: huggingface.co. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 Preview | 0.95 | #193 |
| 2 | O1 Mini | 0.94 | #323 |
| 3 | GPT-4o (2024-08-06) | 0.89 | #336 |
| 4 | Claude 3.5 Sonnet | 0.88 | #350 |
| 5 | DeepSeek V2.5 | 0.83 | #489 |
| 6 | Mistral Large 2 (Jul) | 0.78 | #484 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=webapp1k-react · How It Works · Data refreshed daily, snapshot 2026-10-20.