# Toolathlon → CyberGym

Calibration · https://benchgap.net/calibration/1517 · data retrieved 2026-10-29

CyberGym is estimated from Toolathlon with a offset logistic curve fitted on 10 models measured on both: y = 0.4319 + (0.7816 − 0.4319) / (1 + exp(−106.68·(x − 0.4473))), R² = 0.77, cross-validated error 8.6 pp. It is used for 0 estimates.

## Fitted on

| Model | Toolathlon | CyberGym |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 43.5% | 50.6% |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 47.8% | 76.7% |
| [DeepSeek V4 Pro 0813](https://benchgap.net/model/deepseek-v4-pro-0813.md) | 51.8% | 83.3% |
| [GLM-5](https://benchgap.net/model/glm-5.md) | 38.0% | 43.2% |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 54.6% | 79.0% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 55.6% | 81.8% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 53.4% | 77.9% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 58.0% | 84.5% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 53.1% | 81.8% |
| [Muse Spark 1.1](https://benchgap.net/model/muse-spark-1-1.md) | 75.6% | 59.0% |