WebApp1k-Duo-React: leaderboard
WebApp1K Duo variant requiring two coordinated React feature implementations per task, testing multi-feature code generation.
Metric: pass@1. Source: huggingface.co. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.5 Sonnet | 0.68 | #350 |
| 2 | O1 Mini | 0.67 | #323 |
| 3 | O1 Preview | 0.65 | #193 |
| 4 | GPT-4o (2024-08-06) | 0.53 | #336 |
| 5 | DeepSeek V2.5 | 0.49 | #489 |
| 6 | Mistral Large 2 (Jul) | 0.45 | #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-duo-react · How It Works · Data refreshed daily, snapshot 2026-10-20.