# VulcanBench Frontier v4 → DeepSWE

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

DeepSWE is estimated from VulcanBench Frontier v4 with a Hill curve fitted on 15 models measured on both: y = 0.0000 + (0.7887 − 0.0000)·x^6.00 / (0.59814^6.00 + x^6.00), R² = 0.76, cross-validated error 6.5 pp. It is used for 1 estimate.

| Estimated model | VulcanBench Frontier v4 | DeepSWE | Source |
|---|---|---|---|
| [GPT-6.1 Terra](https://benchgap.net/model/gpt-6-1-terra.md) | 90.0% | 72.6% | estimated ± 6.5 pp, medium confidence |

## Fitted on

| Model | VulcanBench Frontier v4 | DeepSWE |
|---|---|---|
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 91.8% | 67.4% |
| [Claude Fable 5.2](https://benchgap.net/model/claude-fable-5-2.md) | 93.9% | 74.3% |
| [Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5.md) | 91.1% | 74.2% |
| [Claude Sonnet 5.5](https://benchgap.net/model/claude-sonnet-5-5.md) | 92.0% | 71.0% |
| [DeepSeek V4.1 Flash 1017](https://benchgap.net/model/deepseek-v4-1-flash.md) | 88.6% | 77.0% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 84.2% | 67.2% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 87.2% | 72.7% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 89.1% | 69.6% |
| [GPT-6.1 Sol](https://benchgap.net/model/gpt-6-1-sol.md) | 88.8% | 71.9% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 89.3% | 74.1% |
| [GPT-6 Luna](https://benchgap.net/model/gpt-6-luna.md) | 71.9% | 66.6% |
| [GPT-6 Sol](https://benchgap.net/model/gpt-6-sol.md) | 86.8% | 68.8% |
| [Grok 4.7](https://benchgap.net/model/grok-4-7.md) | 93.2% | 71.0% |
| [Muse Wonder Full](https://benchgap.net/model/muse-wonder-full.md) | 88.4% | 79.0% |
| [Beam 1.0 501B-A23B](https://benchgap.net/model/reflection-beam.md) | 64.7% | 43.3% |
