# SWE-bench Pro → SciCode

Calibration · https://benchgap.net/calibration/1470 · data retrieved 2026-10-29

SciCode is estimated from SWE-bench Pro with a linear curve fitted on 19 models measured on both: y = 0.4180·x + 0.2421, R² = 0.61, cross-validated error 5.6 pp. It is used for 3 estimates.

| Estimated model | SWE-bench Pro | SciCode | Source |
|---|---|---|---|
| [Hy4 preview](https://benchgap.net/model/hy4-preview.md) | 65.7% | 51.7% | estimated ± 5.6 pp, medium confidence |
| [Atria Dawn Preview](https://benchgap.net/model/atria-dawn-preview.md) | 59.6% | 49.1% | estimated ± 5.6 pp, medium confidence |
| [Laguna S 2.1](https://benchgap.net/model/laguna-s-2-1.md) | 59.4% | 49.0% | estimated ± 5.6 pp, medium confidence |

## Fitted on

| Model | SWE-bench Pro | SciCode |
|---|---|---|
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 55.1% | 53.1% |
| [Granite 4.2 30B](https://benchgap.net/model/granite-4-2-30b.md) | 33.3% | 38.8% |
| [Granite 4.2 8B](https://benchgap.net/model/granite-4-2-8b.md) | 19.1% | 36.1% |
| [Inkling-Small](https://benchgap.net/model/inkling-small.md) | 55.9% | 48.7% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 58.6% | 52.2% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 50.7% | 48.7% |
| [Ling 3.0 Flash](https://benchgap.net/model/ling-3-0-flash.md) | 56.6% | 41.2% |
| [MiniCPM5-2B](https://benchgap.net/model/minicpm5-2b.md) | 14.4% | 26.3% |
| [Muse Glimmer 30B](https://benchgap.net/model/muse-glimmer-30b.md) | 51.2% | 43.6% |
| [Qwen 3.6 Max (preview)](https://benchgap.net/model/qwen3-6-max-preview.md) | 57.3% | 47.0% |
| [Qwen3.7 Max](https://benchgap.net/model/qwen3-7-max.md) | 60.6% | 53.5% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 57.6% | 51.3% |
| [Beam 1.0 501B-A23B](https://benchgap.net/model/reflection-beam.md) | 66.1% | 49.2% |
| [Beam 1.0 501B-A23B FP8](https://benchgap.net/model/reflection-beam-fp8.md) | 65.9% | 48.3% |
| [Beam 1.0 501B-A23B NVFP4](https://benchgap.net/model/reflection-beam-nvfp4.md) | 65.6% | 46.9% |
| [Sage-A1.5](https://benchgap.net/model/sage-a1-5.md) | 61.2% | 44.3% |
| [Sakana Fugu](https://benchgap.net/model/sakana-fugu.md) | 59.0% | 60.1% |
| [Sakana Fugu-Ultra](https://benchgap.net/model/sakana-fugu-ultra.md) | 73.7% | 58.7% |
| [Spark-X2.6-4B](https://benchgap.net/model/spark-x2-6-4b.md) | 54.3% | 36.8% |