# SWE-Atlas Codebase QnA → DeepSWE

Calibration · https://benchgap.net/calibration/1452 · data retrieved 2026-10-29

DeepSWE is estimated from SWE-Atlas Codebase QnA with a Michaelis–Menten + offset curve fitted on 6 models measured on both: y = 0.0000 + 1.4005·x / (0.70693 + x), R² = 0.78, cross-validated error 8.5 pp. It is used for 0 estimates.

## Fitted on

| Model | SWE-Atlas Codebase QnA | DeepSWE |
|---|---|---|
| [Ling 3.1 Flash](https://benchgap.net/model/ling-3-1-flash.md) | 64.5% | 59.7% |
| [Muse Spark 1.3](https://benchgap.net/model/muse-spark-1-3.md) | 59.4% | 75.4% |
| [Muse Spark Open](https://benchgap.net/model/muse-spark-open.md) | 58.0% | 60.0% |
| [Beam 1.0 501B-A23B](https://benchgap.net/model/reflection-beam.md) | 31.8% | 43.3% |
| [Beam 1.0 501B-A23B FP8](https://benchgap.net/model/reflection-beam-fp8.md) | 32.2% | 43.0% |
| [Beam 1.0 501B-A23B NVFP4](https://benchgap.net/model/reflection-beam-nvfp4.md) | 31.4% | 42.7% |