Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Coding benchmark
Every model the catalog carries a published React Native Evals value for, ranked by that value.
An open benchmark for AI coding agents on real-world React Native implementation tasks, emphasizing working app behavior, recommended architecture choices, and strict constraint adherence. 16 models in the ModelChoice catalog have a published value.
Each point is a model with a published React Native Evals value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
16 models with a published React Native Evals value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Framework-specific app development evaluation |
|---|---|---|---|
| 1 | Cursor | 96.1 | |
| 2 | Cursor | 94.9 | |
| 3 | OpenAI | 85.3 |
What the benchmark measures and how its value is published, from the source’s own record.
React Native Evals is a coding benchmark published by React Native Evals. An open benchmark for AI coding agents on real-world React Native implementation tasks, emphasizing working app behavior, recommended architecture choices, and strict constraint adherence. Its evaluation set is described by the source as react Native app implementation tasks. The source rates its difficulty as production mobile app engineering.
Each model's result is published by React Native Evals as framework-specific app development evaluation. ModelChoice prints that value exactly as published, and never converts or rescales it. This page ranks the 16 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 | OpenAI | 84.7 |
| 5 | Anthropic | 84.1 |
| 6 | Anthropic | 82.8 |
| 7 | Anthropic | 80.6 |
| 8 | 78.9 |
| 9 | Moonshot AI | 77.2 |
| 10 | 75.2 |
| 11 | Z.AI | 74.8 |
| 12 | xAI | 72.6 |
| 13 | OpenAI | 71.6 |
| 14 | DeepSeek | 71.5 |
| 15 | MiniMax | 71.4 |
| 16 | OpenAI | 71 |
Evidence key: Observed
Rows are ordered by the value React Native Evals published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.