List your company

Jailbreak Attack on Welsh Single-Turn 1.0 (test)

84Attack Success Rate (ASR)Claude 3 Sonnet
8.0827.7947.567.21Apr 13, 2025

Evaluation results

MethodLinks
Claude 3 SonnetTurn Type=Single-Turn, Format=Welsh2025.0484
Claude 3 HaikuTurn Type=Single-Turn, Format=Welsh2025.0461
GPT-4 PreviewTurn Type=Single-Turn, Format=Welsh2025.0458
GPT-3.5 TurboTurn Type=Single-Turn, Format=Welsh2025.0448
Claude 3 OpusTurn Type=Single-Turn, Format=Welsh2025.0411