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

Logical Reasoning on LogiQA-2

83.8Accuracy

GPT-5

Updated 4d ago

Evaluation Results

Method	Links
GPT-5 2026.01		83.8
Gemini2.5-Pro 2026.01		78.9
GPT-4.1 2026.01		78.2
SE-GPT 2024.07		76.1
GPT-4o 2026.01		72.9
Zero-shot 2024.07		70.6
Self-EXP 2024.07		69.8
Zero-shot-CoT 2024.07		68.6
ATLAS (cluster) 2026.01		66.8
Self-ICL 2024.07		65.1
ATLAS (RL) 2026.01		62.7
Self-ICL-CoT 2024.07		60.7
SE-GPT 2024.07		55.6
Zero-shot-CoT 2024.07		52.2
Zero-shot 2024.07		51.6
Self-EXP 2024.07		51.5
Modified Self-ICL 2024.07		51
RouterDC 2026.01		50.4
Random Router 2026.01		49.2
RouterDC 2026.01		47.2
BertRouter 2026.01		47.1
ATLAS (cluster) 2026.01		45.6
ZS Router 2026.01		45.3
AutoP-ICL 2024.07		42.2
MLPRouter 2026.01		41.2
FS Router 2026.01		40.8
BertRouter 2026.01		40.3
MLPRouter 2026.01		38.9
CPMI 2026.04		37.71
CPMI_Merge 2026.04		35.66
Self-ICL-CoT 2024.07		35
Self-ICL 2024.07		34.9
MC 2026.04		33.39
Rand_Merge 2026.04		24.54