List your company

Logical Reasoning Oversight on GGC

100AUCBlack
8790.37593.7597.125Jun 1, 2026

Evaluation results

MethodLinks
BlackModel=Gemma2026.0610000
BlackModel=GPT-4o-mini2026.0610000
BlackModel=Qwen2026.0610000
Pipeline 1Model=Gemma, Strategy=B3, Variant=pv12026.0699.900
Pipeline 1Model=Gemma, Strategy=B4, Variant=pv32026.0699.900
Pipeline 1Model=Qwen, Strategy=B4, Variant=pv32026.0699.700.016
Pipeline 1Model=Qwen, Strategy=B2, Variant=pv32026.0699.700.003
Pipeline 1Model=GPT-4o-mini, Strategy=B4, Variant=pv12026.0699.300.072
Pipeline 1Model=GPT-4o-mini, Strategy=B4, Variant=pv22026.069900.096
Pipeline 2Model=Gemma, Strategy=B3, Variant=pv42026.0695.60.060.4
Pipeline 2Model=Gemma, Strategy=B3, Variant=pv22026.0695.40.060.417
Pipeline 2Model=GPT-4o-mini, Strategy=B1, Variant=pv32026.0693.30.2130.481
Pipeline 2Model=GPT-4o-mini, Strategy=B3, Variant=pv12026.0693.30.2170.484
Pipeline 2Model=Qwen, Strategy=B2, Variant=pv42026.0692.20.3190.659
Pipeline 2Model=Qwen, Strategy=B4, Variant=pv12026.0692.10.3380.669
GreenModel=Gemma2026.0691.60.4080.704
GreenModel=Qwen2026.0687.90.5870.793
GreenModel=GPT-4o-mini2026.0687.50.6020.801