# AA Tau3 Banking → AA Agentic Index

Calibration · https://benchgap.net/calibration/aa-tau3-banking/current/to/aa-agentic-index/current · data retrieved 2026-11-18

AA Agentic Index is estimated from AA Tau3 Banking with a inverse Michaelis–Menten curve fitted on 15 models measured on both: y = 1.69726·(x − 0.0000) / (0.0000 + 2.0000 − x), R² = 0.66, cross-validated error 5.5 pp. It is used for 2 estimates.

| Estimated model | AA Tau3 Banking | AA Agentic Index | Source |
|---|---|---|---|
| [Inkling 2 Small](https://benchgap.net/model/inkling-2-small.md) | 40.4% | 43.0% | estimated ± 5.5 pp, medium confidence |
| [Ling 3.0 Flash Fin](https://benchgap.net/model/ling-3-0-flash-fin.md) | 38.6% | 40.6% | estimated ± 5.5 pp, medium confidence |

## Fitted on

| Model | AA Tau3 Banking | AA Agentic Index |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 38.1% | 51.0% |
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 47.2% | 58.0% |
| [Claude Sonnet 5](https://benchgap.net/model/claude-sonnet-5.md) | 37.3% | 44.3% |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 39.4% | 41.7% |
| [DeepSeek V4 Pro](https://benchgap.net/model/deepseek-v4-pro.md) | 39.6% | 49.6% |
| [GLM-5.3](https://benchgap.net/model/glm-5-3.md) | 50.3% | 53.4% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 39.0% | 37.3% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 44.3% | 50.5% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 40.2% | 43.7% |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 42.1% | 42.1% |
| [Grok 4.6](https://benchgap.net/model/grok-4-6.md) | 50.7% | 53.4% |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 46.0% | 50.6% |
| [Ling 3.0 Flash](https://benchgap.net/model/ling-3-0-flash.md) | 28.0% | 21.0% |
| [Muse Spark 1.3](https://benchgap.net/model/muse-spark-1-3.md) | 50.5% | 55.7% |
| [Qwen3.8-27B](https://benchgap.net/model/qwen3-8-27b.md) | 48.0% | 46.5% |
