List your company

Safety discovery in text-based scenarios on Ticket Handling Boat Race

30R ScoreCoT
9.214.62025.4Apr 25, 2026

Evaluation results

MethodLinks
CoTModel=Claude Sonnet 4.62026.04301050
StaticModel=Claude Sonnet 4.62026.04301050
Reward-OnlyModel=Gemini 3 Flash2026.04301050
CoTModel=Gemini 3 Flash2026.04301050
StaticModel=Gemini 3 Flash2026.04301050
Reward-OnlyModel=Claude Sonnet 4.62026.0414116
EPO-SafeModel=Claude Sonnet 4.62026.0410100
EPO-SafeModel=Gemini 3 Flash2026.0410100