# React Native Evals → SWE-bench Verified

Calibration · https://benchgap.net/calibration/reactnativeevals/current/to/swe-bench-verified/current · data retrieved 2026-11-18

SWE-bench Verified is estimated from React Native Evals with a offset logistic curve fitted on 7 models measured on both: y = 0.0000 + (0.8321 − 0.0000) / (1 + exp(−33.57·(x − 0.6812))), R² = 0.92, cross-validated error 5.0 pp. It is used for 2 estimates.

| Estimated model | React Native Evals | SWE-bench Verified | Source |
|---|---|---|---|
| [Composer 2 Fast](https://benchgap.net/model/composer-2-fast.md) | 94.9% | 83.2% | estimated ± 5.0 pp, low confidence |
| [Gemma 4 31B](https://benchgap.net/model/gemma-4-31b.md) | 75.2% | 76.1% | estimated ± 5.0 pp, medium confidence |

## Fitted on

| Model | React Native Evals | SWE-bench Verified |
|---|---|---|
| [Claude Opus 4.6](https://benchgap.net/model/claude-opus-4-6.md) | 84.1% | 80.8% |
| [Claude Opus 4.7](https://benchgap.net/model/claude-opus-4-7.md) | 82.8% | 87.6% |
| [Claude Sonnet 4.6](https://benchgap.net/model/claude-sonnet-4-6.md) | 80.6% | 79.6% |
| [GLM-5](https://benchgap.net/model/glm-5.md) | 74.8% | 77.8% |
| [GPT-OSS 120B](https://benchgap.net/model/gpt-oss-120b.md) | 71.6% | 62.4% |
| [GPT-OSS 20B](https://benchgap.net/model/gpt-oss-20b.md) | 71.0% | 60.7% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 77.2% | 76.8% |
