# WildGuardTest (Decision Index) → HLE-MultiChoice (Decision Index)

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

HLE-MultiChoice (Decision Index) is estimated from WildGuardTest (Decision Index) with a linear curve fitted on 19 models measured on both: y = 0.5684·x + -0.3896, R² = 0.35, cross-validated error 2.6 pp. It is used for 0 estimates.

## Fitted on

| Model | WildGuardTest (Decision Index) | HLE-MultiChoice (Decision Index) |
|---|---|---|
| [Celeris-1.1 Decision](https://benchgap.net/model/celeris-1-1-decision.md) | 94.9% | 12.5% |
| [Celeris-1 Decision](https://benchgap.net/model/celeris-1-decision.md) | 93.3% | 13.3% |
| [Clef](https://benchgap.net/model/cloudflare-clef.md) | 90.7% | 11.1% |
| [Clef-Flash](https://benchgap.net/model/cloudflare-clef-flash.md) | 90.9% | 10.3% |
| [Clef-Omni](https://benchgap.net/model/cloudflare-clef-omni.md) | 87.2% | 9.0% |
| [d1-ultra](https://benchgap.net/model/d1-ultra.md) | 95.4% | 15.0% |
| [Drex Max](https://benchgap.net/model/drex-max.md) | 95.5% | 16.0% |
| [Drex Max v1.1](https://benchgap.net/model/drex-max-v1-1.md) | 95.5% | 17.0% |
| [Drex v1.5](https://benchgap.net/model/drex-v1-5.md) | 86.9% | 12.1% |
| [Drex v2.0](https://benchgap.net/model/drex-v2-0.md) | 87.9% | 13.6% |
| [elephant-1](https://benchgap.net/model/elephant-1.md) | 93.3% | 18.3% |
| [GLiDE](https://benchgap.net/model/fastino-glide.md) | 95.1% | 10.5% |
| [GLiDE v1.2](https://benchgap.net/model/fastino-glide-v1-2.md) | 95.4% | 17.5% |
| [Jev 1.14](https://benchgap.net/model/jev-1-14.md) | 93.1% | 18.9% |
| [d1](https://benchgap.net/model/liquid-d1.md) | 90.9% | 11.5% |
| [Mercury Decide](https://benchgap.net/model/mercury-decide.md) | 88.0% | 10.1% |
| [Microsoft-Decision-1](https://benchgap.net/model/microsoft-decision-1.md) | 88.2% | 10.9% |
| [Perplexity Decider Flash v1.2 4B](https://benchgap.net/model/pplx-decider-flash-v1-2.md) | 93.3% | 12.1% |
| [Perplexity Decider v1.2 27B](https://benchgap.net/model/pplx-decider-v1-2.md) | 94.4% | 14.6% |
