Skip to main content
BenchLM
Data

React Native Evals

Data verified

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.

Top models on React Native Evals — November 21, 2026

As of November 21, 2026, Composer 2 leads the React Native Evals leaderboard with 96.1% , followed by Composer 2 Fast (94.9%) and GPT-5.4 (85.3%).

16 modelsCoding2% of Coding reference weightCurrentUpdated November 21, 2026

Leaderboard (16 models)

React Native Evals leaderboard
RankModel / configurationScoreParameters (B)Open / closed
1Composer 2CursorRun by React Native Evals
96.1%
Not reportedClosed
2Composer 2 FastCursorRun by React Native Evals
94.9%
Not reportedClosed
3GPT-5.4OpenAIRun by React Native Evals
85.3%
Not reportedClosed
4GPT-5.5OpenAIRun by React Native Evals
84.7%
Not reportedClosed
5Claude Opus 4.6AnthropicRun by React Native Evals
84.1%
Not reportedClosed
6Claude Opus 4.7AnthropicRun by React Native Evals
82.8%
Not reportedClosed
7Claude Sonnet 4.6AnthropicRun by React Native Evals
80.6%
Not reportedClosed
8Gemini 3.1 ProGoogleRun by React Native Evals
78.9%
Not reportedClosed
9Kimi K2.5Moonshot AIRun by React Native Evals
77.2%
Not reportedOpen
10Gemma 4 31BGoogleRun by React Native Evals
75.2%
Not reportedOpen
11GLM-5Z.AIRun by React Native Evals
74.8%
Not reportedOpen
12Grok 4xAIRun by React Native Evals
72.6%
Not reportedClosed
13GPT-OSS 120BOpenAIRun by React Native Evals
71.6%
Not reportedOpen
14DeepSeek V3.2DeepSeekRun by React Native Evals
71.5%
Not reportedOpen
15MiniMax M2.7MiniMaxRun by React Native Evals
71.4%
Not reportedOpen
16GPT-OSS 20BOpenAIRun by React Native Evals
71%
Not reportedOpen
  • Lab-reported
  • Benchmark-run
  • Independent
What the labels mean

According to BenchLM.ai, Composer 2 leads the React Native Evals benchmark with a score of 96.1%, followed by Composer 2 Fast (94.9%) and GPT-5.4 (85.3%). There is significant spread across the leaderboard, making this benchmark effective at differentiating model capabilities.

16 models have been evaluated on React Native Evals. The benchmark falls in the Coding category. BenchAlign v6.0 gives React Native Evals 2% of the Coding reference weight, so it moves the Coding leaderboard and the overall ranking. Reference weights are relative weights in the calibrated model, not fixed shares of a score.

About React Native Evals

Year

2026

Tasks

React Native app implementation tasks

Format

Framework-specific app development evaluation

Difficulty

Production mobile app engineering

React Native Evals focuses on framework-specific mobile work that generic coding benchmarks often miss. The public dashboard groups tasks into areas like navigation, animation, and async state, with repeated runs and cost tracking across models.

Freshness and provenance

Version

React Native Evals 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

Current

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does React Native Evals measure?

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.

Which model scores highest on React Native Evals?

Composer 2 by Cursor currently leads with a score of 96.1% on React Native Evals.

How many models are evaluated on React Native Evals?

16 AI models have published results on React Native Evals in the BenchLM catalog.

Last updated: November 21, 2026 · BenchLM version React Native Evals 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 7,000+ subscribers.

One email each week. Unsubscribe anytime.