# Toolathlon → AA ITBench

Calibration · https://benchgap.net/calibration/1512 · data retrieved 2026-10-29

AA ITBench is estimated from Toolathlon with a inverse Michaelis–Menten curve fitted on 7 models measured on both: y = 1.24050·(x − 0.0000) / (0.0000 + 2.0000 − x), R² = 0.41, cross-validated error 6.1 pp. It is used for 0 estimates.

## Fitted on

| Model | Toolathlon | AA ITBench |
|---|---|---|
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 56.5% | 40.3% |
| [GLM-5.2](https://benchgap.net/model/glm-5-2.md) | 48.2% | 42.7% |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 42.9% | 35.2% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 55.6% | 45.8% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 53.4% | 40.3% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 58.0% | 56.2% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 53.1% | 51.0% |