# SWE-bench Pro → DeepSWE

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

DeepSWE is estimated from SWE-bench Pro with a Michaelis–Menten + offset curve fitted on 25 models measured on both: y = 0.0000 + 2.0000·x / (1.68402 + x), R² = 0.30, cross-validated error 11.2 pp. It is used for 10 estimates.

| Estimated model | SWE-bench Pro | DeepSWE | Source |
|---|---|---|---|
| [Claude Mythos 5](https://benchgap.net/model/claude-mythos-5.md) | 80.3% | 64.6% | estimated ± 11.2 pp, low confidence |
| [Atria Dawn Preview](https://benchgap.net/model/atria-dawn-preview.md) | 59.6% | 52.3% | estimated ± 11.2 pp, low confidence |
| [Claude Opus 4.6](https://benchgap.net/model/claude-opus-4-6.md) | 53.4% | 48.2% | estimated ± 11.2 pp, low confidence |
| [MAI-Thinking-1](https://benchgap.net/model/mai-thinking-1.md) | 52.8% | 47.7% | estimated ± 11.2 pp, low confidence |
| [Laguna M.1](https://benchgap.net/model/laguna-m-1.md) | 49.2% | 45.2% | estimated ± 11.2 pp, low confidence |
| [Laguna XS 2.1](https://benchgap.net/model/laguna-xs-2-1.md) | 47.6% | 44.1% | estimated ± 11.2 pp, low confidence |
| [Laguna XS.2](https://benchgap.net/model/laguna-xs-2.md) | 46.3% | 43.1% | estimated ± 11.2 pp, low confidence |
| [LongCat-Flash-Lite-Sparse](https://benchgap.net/model/longcat-flash-lite-sparse.md) | 40.6% | 38.9% | estimated ± 11.2 pp, low confidence |
| [LLaDA2.2-flash](https://benchgap.net/model/llada2-2-flash.md) | 30.1% | 30.3% | estimated ± 11.2 pp, low confidence |
| [Mellum2.1-12B-A2.5B-Thinking](https://benchgap.net/model/mellum2-1-12b-a2-5b-thinking.md) | 28.0% | 28.5% | estimated ± 11.2 pp, low confidence |

## Fitted on

| Model | SWE-bench Pro | DeepSWE |
|---|---|---|
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 81.2% | 67.4% |
| [Claude Fable 5.2](https://benchgap.net/model/claude-fable-5-2.md) | 93.0% | 74.3% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 79.2% | 68.8% |
| [Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5.md) | 89.9% | 74.2% |
| [Claude Sonnet 5.5](https://benchgap.net/model/claude-sonnet-5-5.md) | 81.3% | 71.0% |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 52.6% | 54.4% |
| [DeepSeek V4 Pro](https://benchgap.net/model/deepseek-v4-pro.md) | 55.4% | 62.7% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 62.7% | 67.2% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 64.6% | 72.7% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 63.4% | 69.6% |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 64.7% | 53.0% |
| [Hy4 preview](https://benchgap.net/model/hy4-preview.md) | 65.7% | 64.3% |
| [Laguna S 2.1](https://benchgap.net/model/laguna-s-2-1.md) | 59.4% | 40.4% |
| [Ling 3.1 Flash](https://benchgap.net/model/ling-3-1-flash.md) | 68.7% | 59.7% |
| [Muse Spark 1.1](https://benchgap.net/model/muse-spark-1-1.md) | 61.5% | 53.3% |
| [Ornith-1.5-35B-A3B](https://benchgap.net/model/ornith-1-5-35b-a3b.md) | 59.6% | 22.0% |
| [Ornith-1.5-397B](https://benchgap.net/model/ornith-1-5-397b.md) | 65.1% | 56.0% |
| [Qwen3.8-27B](https://benchgap.net/model/qwen3-8-27b.md) | 61.7% | 42.2% |
| [Qwen3.8-Flash-Next](https://benchgap.net/model/qwen3-8-flash-next.md) | 62.5% | 58.7% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 67.7% | 56.6% |
| [Qwen3.8-Omni-Flash](https://benchgap.net/model/qwen3-8-omni-flash.md) | 63.3% | 57.8% |
| [Beam 1.0 501B-A23B](https://benchgap.net/model/reflection-beam.md) | 66.1% | 43.3% |
| [Beam 1.0 501B-A23B FP8](https://benchgap.net/model/reflection-beam-fp8.md) | 65.9% | 43.0% |
| [Beam 1.0 501B-A23B NVFP4](https://benchgap.net/model/reflection-beam-nvfp4.md) | 65.6% | 42.7% |
| [Ripple-65B Preview](https://benchgap.net/model/ripple-65b-preview.md) | 61.4% | 44.3% |
