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

Logic Reasoning on ARC-Challenge & LogiQA OpenCompass (test)

38.31ARC-C Accuracy

CRITIQ

35.481236.215636.9537.6844Feb 26, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.02
38.3130.4134.36
2025.02
37.9727.3432.66
2025.02
36.6123.530.06
2025.02
35.5926.8831.24