# ExploitBench Internal Port → ExploitBench

Calibration · https://benchgap.net/calibration/exploitbenchinternalport/current/to/exploitbench/current · data retrieved 2026-11-21

ExploitBench is estimated from ExploitBench Internal Port with a Michaelis–Menten curve fitted on 7 models measured on both: y = 1.0591·x / (0.02302 + x), R² = 0.97, cross-validated error 7.0 pp. It is used for 0 estimates.

## Fitted on

| Model | ExploitBench Internal Port | ExploitBench |
|---|---|---|
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 5.5% | 73.5% |
| [GPT-6.1 Sol](https://benchgap.net/model/gpt-6-1-sol.md) | 21.5% | 99.7% |
| [GPT-6.1 Terra](https://benchgap.net/model/gpt-6-1-terra.md) | 24.5% | 97.1% |
| [GPT-6.2 Astra](https://benchgap.net/model/gpt-6-2-astra.md) | 53.5% | 100.0% |
| [GPT-6.2 Sol](https://benchgap.net/model/gpt-6-2-sol.md) | 50.5% | 100.0% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 39.0% | 100.0% |
| [GPT-6 Cyber](https://benchgap.net/model/gpt-6-cyber.md) | 42.0% | 100.0% |
