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

Question Answering on ARC Easy (Accuracy and CC Metrics)

92.18Accuracy (ARC-E)

Best Model

78.753682.239385.72589.2107Jun 9, 2025Jul 2, 2025Jul 25, 2025Aug 17, 2025Sep 9, 2025Oct 2, 2025Oct 26, 2025
Updated 22d ago

Evaluation Results

MethodLinks
2025.10
92.18----1.14-
2025.10
90.91----1.37-
2025.10
90.36------
2025.06
87.7213.3214.1715.03-1.912.0125.72
2025.06
87.7213.4714.3115.151.8415.0128.38
2025.06
86.7614.9715.8916.821.7614.8827.86
2025.06
84.841.541.822.0839.9347.0953.79
2025.06
84.260.981.351.6837.445.5552.88
2025.06
84.261.561.842.1138.9446.7653.63
2025.06
81.625.586.136.687.9720.7233.14
2025.06
81.625.586.116.668.9921.5334.19
2025.06
81.046.326.877.4211.4823.1634.8
2025.06
80.231.21.622.0133.7743.1551.75
2025.06
80.231.251.662.0334.8844.0252.52
2025.06
79.271.712.072.4337.9746.2453.74