# SciCode → SWE-bench Verified

Calibration · https://benchgap.net/calibration/1408 · data retrieved 2026-10-29

SWE-bench Verified is estimated from SciCode with a Hill curve fitted on 19 models measured on both: y = 0.3879 + (0.8864 − 0.3879)·x^6.00 / (0.38521^6.00 + x^6.00), R² = 0.90, cross-validated error 5.1 pp. It is used for 7 estimates.

| Estimated model | SciCode | SWE-bench Verified | Source |
|---|---|---|---|
| [A.X K2](https://benchgap.net/model/a-x-k2.md) | 41.0% | 68.3% | estimated ± 5.1 pp, medium confidence |
| [Ling 3.0 Flash FP8](https://benchgap.net/model/ling-3-0-flash-fp8.md) | 40.4% | 67.2% | estimated ± 5.1 pp, medium confidence |
| [Mercury 2.5](https://benchgap.net/model/mercury-2-5.md) | 38.0% | 62.7% | estimated ± 5.1 pp, medium confidence |
| [Nemotron 3 Nano Omni 30B A3B](https://benchgap.net/model/nemotron-3-nano-omni-30b-a3b.md) | 32.0% | 51.1% | estimated ± 5.1 pp, medium confidence |
| [Agents-A1-4B](https://benchgap.net/model/agents-a1-4b.md) | 29.6% | 47.3% | estimated ± 5.1 pp, medium confidence |
| [Ling 2.6 Flash](https://benchgap.net/model/ling-2-6-flash.md) | 27.0% | 44.1% | estimated ± 5.1 pp, medium confidence |
| [Granite 4.2 3B](https://benchgap.net/model/granite-4-2-3b.md) | 24.1% | 41.6% | estimated ± 5.1 pp, low confidence |

## Fitted on

| Model | SciCode | SWE-bench Verified |
|---|---|---|
| [Granite 4.2 30B](https://benchgap.net/model/granite-4-2-30b.md) | 38.8% | 57.0% |
| [Granite 4.2 8B](https://benchgap.net/model/granite-4-2-8b.md) | 36.1% | 47.7% |
| [Hy3 Preview](https://benchgap.net/model/hy3-preview.md) | 41.2% | 74.4% |
| [Inkling-Small](https://benchgap.net/model/inkling-small.md) | 48.7% | 80.2% |
| [K-EXAONE 2.0](https://benchgap.net/model/k-exaone-2-0.md) | 37.4% | 68.2% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 52.2% | 80.2% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 48.7% | 76.8% |
| [LFM2.5-24B-A2B](https://benchgap.net/model/lfm2-5-24b-a2b.md) | 32.7% | 51.0% |
| [LFM3-1.7B](https://benchgap.net/model/lfm3-1-7b.md) | 28.5% | 43.4% |
| [MiniCPM5-2B](https://benchgap.net/model/minicpm5-2b.md) | 26.3% | 46.4% |
| [Muse Glimmer 30B](https://benchgap.net/model/muse-glimmer-30b.md) | 43.6% | 76.0% |
| [Nemotron 3.5 Lightning 30B A3B NVFP4](https://benchgap.net/model/nemotron-3-5-lightning-30b-a3b-nvfp4.md) | 31.4% | 52.8% |
| [Nemotron 3 Ultra](https://benchgap.net/model/nemotron-3-ultra.md) | 44.6% | 71.9% |
| [Qwen3.7 Max](https://benchgap.net/model/qwen3-7-max.md) | 53.5% | 80.4% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 51.3% | 77.7% |
| [Beam 1.0 501B-A23B](https://benchgap.net/model/reflection-beam.md) | 49.2% | 81.6% |
| [Beam 1.0 501B-A23B FP8](https://benchgap.net/model/reflection-beam-fp8.md) | 48.3% | 80.2% |
| [Beam 1.0 501B-A23B NVFP4](https://benchgap.net/model/reflection-beam-nvfp4.md) | 46.9% | 80.7% |
| [Spark-X2.6-4B](https://benchgap.net/model/spark-x2-6-4b.md) | 36.8% | 62.8% |