ReactBench v1 Fix React
Code · 2026-07-14
The 24-task Fix React subset of ReactBench v1 asks coding agents to remove targeted React problems without being shown the React Doctor findings. A rollout passes only when the targeted issues are removed, no new graded issue is introduced, and existing behavior remains intact.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.6 Sol | 50.8 |
| GPT-5.6 Terra | 40.8 |
| Grok 4.5 | 35.8 |
| Claude Opus 5 | 32.5 |
| GPT-5.6 Luna | 32.5 |
| Claude Fable 5 | 26.7 |
| GLM-5.2 | 24.2 |
| Muse Spark 1.1 | 21.7 |
| Opus 4.8 | 20.8 |
| Kimi K3 | 19.2 |
| Sonnet 5 | 18.3 |
| Gemini 3.5 Flash | 18.3 |
| Gemini 3.1 Pro Preview | 16.7 |
| Composer 2.5 | 14.2 |
| Kimi K2.7 Code | 14.2 |
| Inkling | 7.5 |