# Toolathlon → GDPval-AA

Calibration · https://benchgap.net/calibration/1518 · data retrieved 2026-10-29

GDPval-AA is estimated from Toolathlon with a Michaelis–Menten + offset curve fitted on 19 models measured on both: y = 0.0000 + 2.0000·x / (2.18253 + x), R² = 0.44, cross-validated error 9.6 pp. It is used for 0 estimates.

## Fitted on

| Model | Toolathlon | GDPval-AA |
|---|---|---|
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 59.9% | 47.7% |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 47.8% | 46.7% |
| [DeepSeek V4 Pro 0813](https://benchgap.net/model/deepseek-v4-pro-0813.md) | 51.8% | 54.5% |
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 56.5% | 42.2% |
| [GLM-5.2](https://benchgap.net/model/glm-5-2.md) | 48.2% | 43.6% |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 54.6% | 37.3% |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 42.9% | 25.6% |
| [GPT-5.4 nano](https://benchgap.net/model/gpt-5-4-nano.md) | 35.5% | 22.4% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 55.6% | 42.5% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 53.4% | 48.0% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 58.0% | 55.4% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 53.1% | 47.6% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 50.0% | 26.9% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 27.8% | 17.0% |
| [MiniMax M2.7](https://benchgap.net/model/minimax-m2-7.md) | 46.3% | 25.5% |
| [Muse Spark 1.1](https://benchgap.net/model/muse-spark-1-1.md) | 75.6% | 35.6% |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 26.9% | 19.6% |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 39.8% | 24.5% |
| [Step 3.7 Flash](https://benchgap.net/model/step-3-7-flash.md) | 49.5% | 25.8% |