# SciCode → Vals SWE-bench

Calibration · https://benchgap.net/calibration/1410 · data retrieved 2026-10-29

Vals SWE-bench is estimated from SciCode with a Hill curve fitted on 8 models measured on both: y = 0.0000 + (0.7966 − 0.0000)·x^6.00 / (0.31757^6.00 + x^6.00), R² = 0.39, cross-validated error 5.3 pp. It is used for 20 estimates.

| Estimated model | SciCode | Vals SWE-bench | Source |
|---|---|---|---|
| [Sakana Fugu](https://benchgap.net/model/sakana-fugu.md) | 60.1% | 78.0% | estimated ± 5.3 pp, low confidence |
| [Step 5 Preview](https://benchgap.net/model/step-5-preview.md) | 58.9% | 77.8% | estimated ± 5.3 pp, low confidence |
| [Sakana Fugu-Ultra](https://benchgap.net/model/sakana-fugu-ultra.md) | 58.7% | 77.7% | estimated ± 5.3 pp, low confidence |
| [Beam 1.0 501B-A23B](https://benchgap.net/model/reflection-beam.md) | 49.2% | 74.3% | estimated ± 5.3 pp, low confidence |
| [Beam 1.0 501B-A23B FP8](https://benchgap.net/model/reflection-beam-fp8.md) | 48.3% | 73.7% | estimated ± 5.3 pp, low confidence |
| [Beam 1.0 501B-A23B NVFP4](https://benchgap.net/model/reflection-beam-nvfp4.md) | 46.9% | 72.7% | estimated ± 5.3 pp, low confidence |
| [Sage-A1.5](https://benchgap.net/model/sage-a1-5.md) | 44.3% | 70.1% | estimated ± 5.3 pp, low confidence |
| [Muse Glimmer 30B](https://benchgap.net/model/muse-glimmer-30b.md) | 43.6% | 69.3% | estimated ± 5.3 pp, low confidence |
| [Hy3 Preview](https://benchgap.net/model/hy3-preview.md) | 41.2% | 65.9% | estimated ± 5.3 pp, low confidence |
| [A.X K2](https://benchgap.net/model/a-x-k2.md) | 41.0% | 65.5% | estimated ± 5.3 pp, low confidence |
| [Ling 3.0 Flash FP8](https://benchgap.net/model/ling-3-0-flash-fp8.md) | 40.4% | 64.4% | estimated ± 5.3 pp, low confidence |
| [Granite 4.2 30B](https://benchgap.net/model/granite-4-2-30b.md) | 38.8% | 61.2% | estimated ± 5.3 pp, low confidence |
| [Mercury 2.5](https://benchgap.net/model/mercury-2-5.md) | 38.0% | 59.4% | estimated ± 5.3 pp, low confidence |
| [K-EXAONE 2.0](https://benchgap.net/model/k-exaone-2-0.md) | 37.4% | 57.9% | estimated ± 5.3 pp, low confidence |
| [Spark-X2.6-4B](https://benchgap.net/model/spark-x2-6-4b.md) | 36.8% | 56.4% | estimated ± 5.3 pp, low confidence |
| [Granite 4.2 8B](https://benchgap.net/model/granite-4-2-8b.md) | 36.1% | 54.4% | estimated ± 5.3 pp, low confidence |
| [LFM2.5-24B-A2B](https://benchgap.net/model/lfm2-5-24b-a2b.md) | 32.7% | 43.4% | estimated ± 5.3 pp, low confidence |
| [Nemotron 3 Nano Omni 30B A3B](https://benchgap.net/model/nemotron-3-nano-omni-30b-a3b.md) | 32.0% | 40.7% | estimated ± 5.3 pp, low confidence |
| [Nemotron 3.5 Lightning 30B A3B NVFP4](https://benchgap.net/model/nemotron-3-5-lightning-30b-a3b-nvfp4.md) | 31.4% | 38.4% | estimated ± 5.3 pp, low confidence |
| [Agents-A1-4B](https://benchgap.net/model/agents-a1-4b.md) | 29.6% | 31.6% | estimated ± 5.3 pp, low confidence |

## Fitted on

| Model | SciCode | Vals SWE-bench |
|---|---|---|
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 53.1% | 78.8% |
| [Grok 4.3](https://benchgap.net/model/grok-4-3.md) | 47.3% | 71.4% |
| [Inkling-Small](https://benchgap.net/model/inkling-small.md) | 48.7% | 82.2% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 52.2% | 76.2% |
| [Ling 3.0 Flash](https://benchgap.net/model/ling-3-0-flash.md) | 41.2% | 65.2% |
| [Nemotron 3 Ultra](https://benchgap.net/model/nemotron-3-ultra.md) | 44.6% | 69.0% |
| [Qwen 3.6 Max (preview)](https://benchgap.net/model/qwen3-6-max-preview.md) | 47.0% | 72.8% |
| [Qwen3.7 Max](https://benchgap.net/model/qwen3-7-max.md) | 53.5% | 68.8% |