Callstack Incubator React Native Evaluation Suite.

A benchmark suite evaluating how AI coding models handle authentic React Native development tasks. 71 evals across 5 categories: animation (14), async-state management (14), lists (19), navigation (14), and React Native APIs (10). Each eval specifies explicit, judgeable requirements. Model outputs are scored on requirement satisfaction using LLM-based judging. Covers real libraries: Reanimated, React Navigation, Zustand, Jotai, React Query, FlatList, FlashList, LegendList.

Best published scores.

40 results indexed across 4 metrics. Shaded row marks current SOTA; ties broken by submission date.

Primary

requirement-satisfaction · higher is better

All metrics

animation-satisfaction, async-state-satisfaction, navigation-satisfaction, requirement-satisfaction

1 steps
of state of the art.

Each row below marks a model that broke the previous record on requirement-satisfaction. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

1. Mar 24, 2026Composer 2Anysphere96.20

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

• 01A public checkpoint or API endpoint
• 02A reproduction script with frozen commit + seed
• 03Declared evaluation environment (Python, deps)
• 04One row per metric declared by this dataset
• 05A contact so we can follow up on discrepancies