# SWE-bench Pro → FrontierSWE v2

Calibration · https://benchgap.net/calibration/1464 · data retrieved 2026-10-29

FrontierSWE v2 is estimated from SWE-bench Pro with a linear curve fitted on 8 models measured on both: y = 1.7808·x + -0.9171, R² = 0.88, cross-validated error 9.0 pp. It is used for 69 estimates.

| Estimated model | SWE-bench Pro | FrontierSWE v2 | Source |
|---|---|---|---|
| [Claude Mythos 5](https://benchgap.net/model/claude-mythos-5.md) | 80.3% | 51.3% | estimated ± 9.0 pp, medium confidence |
| [Sakana Fugu-Ultra](https://benchgap.net/model/sakana-fugu-ultra.md) | 73.7% | 39.5% | estimated ± 9.0 pp, medium confidence |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 69.2% | 31.5% | estimated ± 9.0 pp, medium confidence |
| [Ling 3.1 Flash](https://benchgap.net/model/ling-3-1-flash.md) | 68.7% | 30.7% | estimated ± 9.0 pp, medium confidence |
| [Beam 1.0 501B-A23B](https://benchgap.net/model/reflection-beam.md) | 66.1% | 26.0% | estimated ± 9.0 pp, medium confidence |
| [Beam 1.0 501B-A23B FP8](https://benchgap.net/model/reflection-beam-fp8.md) | 65.9% | 25.6% | estimated ± 9.0 pp, medium confidence |
| [Hy4 preview](https://benchgap.net/model/hy4-preview.md) | 65.7% | 25.3% | estimated ± 9.0 pp, medium confidence |
| [Beam 1.0 501B-A23B NVFP4](https://benchgap.net/model/reflection-beam-nvfp4.md) | 65.6% | 25.1% | estimated ± 9.0 pp, medium confidence |
| [Ornith-1.5-397B](https://benchgap.net/model/ornith-1-5-397b.md) | 65.1% | 24.2% | estimated ± 9.0 pp, medium confidence |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 64.7% | 23.5% | estimated ± 9.0 pp, medium confidence |
| [Claude Opus 4.7 (Adaptive)](https://benchgap.net/model/claude-opus-4-7-adaptive.md) | 64.3% | 22.8% | estimated ± 9.0 pp, medium confidence |
| [Qwen3.8-Omni-Flash](https://benchgap.net/model/qwen3-8-omni-flash.md) | 63.3% | 21.0% | estimated ± 9.0 pp, medium confidence |
| [Qwen3.8-Flash-Next](https://benchgap.net/model/qwen3-8-flash-next.md) | 62.5% | 19.6% | estimated ± 9.0 pp, medium confidence |
| [Ornith-1.0-397B](https://benchgap.net/model/ornith-1-0-397b.md) | 62.2% | 19.1% | estimated ± 9.0 pp, medium confidence |
| [GLM-5.2](https://benchgap.net/model/glm-5-2.md) | 62.1% | 18.9% | estimated ± 9.0 pp, medium confidence |
| [Qwen3.8-27B](https://benchgap.net/model/qwen3-8-27b.md) | 61.7% | 18.2% | estimated ± 9.0 pp, medium confidence |
| [Muse Spark 1.1](https://benchgap.net/model/muse-spark-1-1.md) | 61.5% | 17.8% | estimated ± 9.0 pp, medium confidence |
| [Sage-A1.5](https://benchgap.net/model/sage-a1-5.md) | 61.2% | 17.3% | estimated ± 9.0 pp, medium confidence |
| [dots3-note Preview](https://benchgap.net/model/dots3-note-preview.md) | 61.0% | 16.9% | estimated ± 9.0 pp, medium confidence |
| [Qwen3.7 Max](https://benchgap.net/model/qwen3-7-max.md) | 60.6% | 16.2% | estimated ± 9.0 pp, medium confidence |
| [Atria Dawn Preview](https://benchgap.net/model/atria-dawn-preview.md) | 59.6% | 14.4% | estimated ± 9.0 pp, medium confidence |
| [Ornith-1.5-35B-A3B](https://benchgap.net/model/ornith-1-5-35b-a3b.md) | 59.6% | 14.4% | estimated ± 9.0 pp, medium confidence |
| [Laguna S 2.1](https://benchgap.net/model/laguna-s-2-1.md) | 59.4% | 14.1% | estimated ± 9.0 pp, medium confidence |
| [MiniMax M3](https://benchgap.net/model/minimax-m3.md) | 59.0% | 13.4% | estimated ± 9.0 pp, medium confidence |
| [Sakana Fugu](https://benchgap.net/model/sakana-fugu.md) | 59.0% | 13.4% | estimated ± 9.0 pp, medium confidence |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 58.6% | 12.6% | estimated ± 9.0 pp, medium confidence |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 58.6% | 12.6% | estimated ± 9.0 pp, medium confidence |
| [GLM-5.1](https://benchgap.net/model/glm-5-1.md) | 58.4% | 12.3% | estimated ± 9.0 pp, medium confidence |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 57.7% | 11.0% | estimated ± 9.0 pp, medium confidence |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 57.6% | 10.9% | estimated ± 9.0 pp, medium confidence |
| [Qwen 3.6 Max (preview)](https://benchgap.net/model/qwen3-6-max-preview.md) | 57.3% | 10.3% | estimated ± 9.0 pp, medium confidence |
| [MiMo-V2.5-Pro](https://benchgap.net/model/mimo-v2-5-pro.md) | 57.2% | 10.2% | estimated ± 9.0 pp, medium confidence |
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 57.1% | 10.0% | estimated ± 9.0 pp, medium confidence |
| [GPT-5.3 Codex](https://benchgap.net/model/gpt-5-3-codex.md) | 56.8% | 9.4% | estimated ± 9.0 pp, medium confidence |
| [Ling 3.0 Flash](https://benchgap.net/model/ling-3-0-flash.md) | 56.6% | 9.1% | estimated ± 9.0 pp, medium confidence |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 56.6% | 9.1% | estimated ± 9.0 pp, medium confidence |
| [Step 3.7 Flash](https://benchgap.net/model/step-3-7-flash.md) | 56.3% | 8.6% | estimated ± 9.0 pp, medium confidence |
| [MiniMax M2.7](https://benchgap.net/model/minimax-m2-7.md) | 56.2% | 8.4% | estimated ± 9.0 pp, medium confidence |
| [MiMo-V2.5](https://benchgap.net/model/mimo-v2-5.md) | 56.1% | 8.2% | estimated ± 9.0 pp, medium confidence |
| [Inkling-Small](https://benchgap.net/model/inkling-small.md) | 55.9% | 7.8% | estimated ± 9.0 pp, medium confidence |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 55.6% | 7.3% | estimated ± 9.0 pp, medium confidence |
| [DeepSeek V4 Pro 0813](https://benchgap.net/model/deepseek-v4-pro-0813.md) | 55.4% | 6.9% | estimated ± 9.0 pp, medium confidence |
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 55.1% | 6.4% | estimated ± 9.0 pp, medium confidence |
| [GLM-5](https://benchgap.net/model/glm-5.md) | 55.1% | 6.4% | estimated ± 9.0 pp, medium confidence |
| [Spark-X2.6-4B](https://benchgap.net/model/spark-x2-6-4b.md) | 54.3% | 5.0% | estimated ± 9.0 pp, medium confidence |
| [Gemini 3.5 Flash-Lite](https://benchgap.net/model/gemini-3-5-flash-lite.md) | 54.2% | 4.8% | estimated ± 9.0 pp, low confidence |
| [Qwen3.6-27B](https://benchgap.net/model/qwen3-6-27b.md) | 53.5% | 3.6% | estimated ± 9.0 pp, low confidence |
| [Claude Opus 4.6](https://benchgap.net/model/claude-opus-4-6.md) | 53.4% | 3.4% | estimated ± 9.0 pp, low confidence |
| [MAI-Thinking-1](https://benchgap.net/model/mai-thinking-1.md) | 52.8% | 2.3% | estimated ± 9.0 pp, low confidence |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 52.6% | 2.0% | estimated ± 9.0 pp, low confidence |
| [Muse Spark](https://benchgap.net/model/muse-spark.md) | 52.4% | 1.6% | estimated ± 9.0 pp, low confidence |
| [Grok 4.20](https://benchgap.net/model/grok-4-20-beta.md) | 51.8% | 0.5% | estimated ± 9.0 pp, low confidence |
| [Nemotron 3.5 Super VL 120B A12B](https://benchgap.net/model/nemotron-3-5-super-vl-120b-a12b.md) | 51.8% | 0.5% | estimated ± 9.0 pp, low confidence |
| [Granite 4.2 30B](https://benchgap.net/model/granite-4-2-30b.md) | 33.3% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Granite 4.2 8B](https://benchgap.net/model/granite-4-2-8b.md) | 19.1% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 50.7% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Laguna M.1](https://benchgap.net/model/laguna-m-1.md) | 49.2% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Laguna XS.2](https://benchgap.net/model/laguna-xs-2.md) | 46.3% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Laguna XS 2.1](https://benchgap.net/model/laguna-xs-2-1.md) | 47.6% | 0.0% | estimated ± 9.0 pp, low confidence |
| [LLaDA2.2-flash](https://benchgap.net/model/llada2-2-flash.md) | 30.1% | 0.0% | estimated ± 9.0 pp, low confidence |
| [LongCat-Flash-Lite-Sparse](https://benchgap.net/model/longcat-flash-lite-sparse.md) | 40.6% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Mellum2.1-12B-A2.5B-Thinking](https://benchgap.net/model/mellum2-1-12b-a2-5b-thinking.md) | 28.0% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Muse Glimmer 30B](https://benchgap.net/model/muse-glimmer-30b.md) | 51.2% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Nemotron 3.5 Super VL 120B A12B NVFP4](https://benchgap.net/model/nemotron-3-5-super-vl-120b-a12b-nvfp4.md) | 51.3% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Ornith-1.0-35B](https://benchgap.net/model/ornith-1-0-35b.md) | 50.4% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Ornith-1.0-9B](https://benchgap.net/model/ornith-1-0-9b.md) | 42.9% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Ornith-1.5-9B](https://benchgap.net/model/ornith-1-5-9b.md) | 47.5% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 50.9% | 0.0% | estimated ± 9.0 pp, low confidence |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 49.5% | 0.0% | estimated ± 9.0 pp, low confidence |

## Fitted on

| Model | SWE-bench Pro | FrontierSWE v2 |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 80.0% | 47.0% |
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 81.2% | 56.3% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 79.2% | 52.0% |
| [Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5.md) | 89.9% | 62.3% |
| [Claude Sonnet 5.5](https://benchgap.net/model/claude-sonnet-5-5.md) | 81.3% | 61.9% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 64.6% | 32.2% |
| [Inkling](https://benchgap.net/model/inkling.md) | 54.3% | 4.1% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 67.7% | 15.8% |