# Artificial Analysis Decision Index v1.0 → WildGuardTest (Decision Index)

Calibration · https://benchgap.net/calibration/aa-decision-index/current/to/aa-decision-wild-guard-test/current · data retrieved 2026-11-21

WildGuardTest (Decision Index) is estimated from Artificial Analysis Decision Index v1.0 with a linear curve fitted on 19 models measured on both: y = 0.3071·x + 0.7501, R² = 0.43, cross-validated error 2.5 pp. It is used for 0 estimates.

## Fitted on

| Model | Artificial Analysis Decision Index v1.0 | WildGuardTest (Decision Index) |
|---|---|---|
| [Celeris-1.1 Decision](https://benchgap.net/model/celeris-1-1-decision.md) | 60.9% | 94.9% |
| [Celeris-1 Decision](https://benchgap.net/model/celeris-1-decision.md) | 52.3% | 93.3% |
| [Clef](https://benchgap.net/model/cloudflare-clef.md) | 48.6% | 90.7% |
| [Clef-Flash](https://benchgap.net/model/cloudflare-clef-flash.md) | 45.8% | 90.9% |
| [Clef-Omni](https://benchgap.net/model/cloudflare-clef-omni.md) | 44.3% | 87.2% |
| [d1-ultra](https://benchgap.net/model/d1-ultra.md) | 65.2% | 95.4% |
| [Drex Max](https://benchgap.net/model/drex-max.md) | 63.7% | 95.5% |
| [Drex Max v1.1](https://benchgap.net/model/drex-max-v1-1.md) | 63.8% | 95.5% |
| [Drex v1.5](https://benchgap.net/model/drex-v1-5.md) | 50.7% | 86.9% |
| [Drex v2.0](https://benchgap.net/model/drex-v2-0.md) | 57.9% | 87.9% |
| [elephant-1](https://benchgap.net/model/elephant-1.md) | 64.7% | 93.3% |
| [GLiDE](https://benchgap.net/model/fastino-glide.md) | 53.9% | 95.1% |
| [GLiDE v1.2](https://benchgap.net/model/fastino-glide-v1-2.md) | 65.0% | 95.4% |
| [Jev 1.14](https://benchgap.net/model/jev-1-14.md) | 57.1% | 93.1% |
| [d1](https://benchgap.net/model/liquid-d1.md) | 50.3% | 90.9% |
| [Mercury Decide](https://benchgap.net/model/mercury-decide.md) | 52.7% | 88.0% |
| [Microsoft-Decision-1](https://benchgap.net/model/microsoft-decision-1.md) | 53.8% | 88.2% |
| [Perplexity Decider Flash v1.2 4B](https://benchgap.net/model/pplx-decider-flash-v1-2.md) | 50.2% | 93.3% |
| [Perplexity Decider v1.2 27B](https://benchgap.net/model/pplx-decider-v1-2.md) | 56.2% | 94.4% |
