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

Math on GSM8K (Workspace Metrics)

100True Workspace Rate

PromptCOS

9.5233.0156.579.99Sep 3, 2025
Updated 9d ago

Evaluation Results

MethodLinks
2025.09
100210.72
2025.09
100170.64
2025.09
10070.89
2025.09
9850.91
2025.09
83790.03
2025.09
82120.65
2025.09
76610.03
2025.09
7472-0.02
2025.09
5670.45
2025.09
5420.49
2025.09
4510.42
2025.09
1300.11