Share your thoughts, 1 month free Claude Pro on usSee more

Logical Reasoning on Logical Deduction

81.03Pass@1

MAPR

Updated 1d ago

Evaluation Results

Method	Links
MAPR 2025.09		81.03	-
GRPO 2025.09		80.81	-
HtT 2025.06		1	-
RGFB 2025.06		1	-
Chain-of-Logic 2025.06		1	-
OpenAI o3-mini 2025.06		1	-
DeepSeek-R1 2025.06		0.983	-
RULEREASONER-8B 2025.06		0.983	0.4
Claude-3.7-Sonnet 2025.06		0.97	-
ADARFT 2025.06		0.966	-
RULEREASONER-4B 2025.06		0.963	0.2
Easy-to-hard RL 2025.06		0.96	-
DAPO 2025.06		0.953	-
Data-balance RL 2025.06		0.953	-
GRPO 2025.06		0.903	-
OpenAI o1 2025.06		0.88	-
SFT w/ Short CoT 2025.06		0.876	-
SFT w/o CoT 2025.06		0.859	-
Dr. GRPO 2025.06		0.843	-
SFT w/ Long CoT 2025.06		0.796	-