# QwenReactBench

> Qwen's internal benchmark for building and rendering bilingual React projects across seven categories.

Canonical page: https://benchlm.ai/benchmarks/qwenreactbench

- Category: [Coding](/coding)
- Last updated: September 27, 2026

## About QwenReactBench

- Year: 2026
- Tasks: Bilingual React project construction
- Format: Bradley-Terry/Elo rating
- Difficulty: Production frontend development
- Paper: [Qwen3.8-Max: A New Bar for Coding and Cowork](https://qwen.ai/blog?id=qwen3.8)

Qwen evaluates the benchmark with the Claude Code harness, automatic rendering, and a multimodal judge, then reports a Bradley-Terry/Elo rating. We keep the provider-internal result display-only and preserve its rating scale rather than treating it as a percentage.

QwenReactBench is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Qwen3.8 Max](/models/qwen3-8-max) | Alibaba | 1724 |

## FAQ

### What does QwenReactBench measure?

Qwen's internal benchmark for building and rendering bilingual React projects across seven categories.

### Which model scores highest on QwenReactBench?

Qwen3.8 Max by Alibaba currently leads with a score of 1724 on QwenReactBench.

### How many models are evaluated on QwenReactBench?

1 AI models have been evaluated on QwenReactBench on BenchLM.

### Does QwenReactBench affect BenchLM's overall score?

Not directly. QwenReactBench is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.