# PostTrainBench v1.1 → Vals SWE-bench

Calibration · https://benchgap.net/calibration/posttrainbench%23posttrainbench-v1-1/current/to/valsswebench/current · data retrieved 2026-11-18

Vals SWE-bench is estimated from PostTrainBench v1.1 with a Hill curve fitted on 10 models measured on both: y = 0.7868 + (1.2000 − 0.7868)·x^6.00 / (0.38364^6.00 + x^6.00), R² = 0.74, cross-validated error 4.1 pp. It is used for 1 estimate.

| Estimated model | PostTrainBench v1.1 | Vals SWE-bench | Source |
|---|---|---|---|
| [MiniMax M3.1 Flash](https://benchgap.net/model/minimax-m3-1-flash.md) | 39.3% | 100.0% | estimated ± 4.1 pp, medium confidence |

## Fitted on

| Model | PostTrainBench v1.1 | Vals SWE-bench |
|---|---|---|
| [Claude Opus 4.7](https://benchgap.net/model/claude-opus-4-7.md) | 28.6% | 82.0% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 32.9% | 88.6% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 35.0% | 97.0% |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 22.0% | 78.8% |
| [GLM-5.2](https://benchgap.net/model/glm-5-2.md) | 31.7% | 82.8% |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 19.0% | 78.2% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 27.2% | 82.6% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 36.2% | 96.2% |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 23.5% | 86.6% |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 32.0% | 93.4% |
