Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Math on GSM8K (Workspace Metrics)
Loading...
100
True Workspace Rate
PromptCOS
9.52
33.01
56.5
79.99
Sep 3, 2025
True Workspace Rate
False Workspace Rate
Min Workspace Distance
Updated 9d ago
Evaluation Results
Method
Method
Links
True Workspace Rate
False Workspace Rate
Min Workspace Distance
PromptCOS
Model=TinyLlama-chat
2025.09
100
21
0.72
PromptCOS
Model=Deepseek-d-qwen
2025.09
100
17
0.64
PromptCOS
Model=Gemma2-it
2025.09
100
7
0.89
PCG
Model=Gemma2-it
2025.09
98
5
0.91
PR
Model=Gemma2-it
2025.09
83
79
0.03
PCG
Model=TinyLlama-chat
2025.09
82
12
0.65
PR
Model=TinyLlama-chat
2025.09
76
61
0.03
PR
Model=Deepseek-d-qwen
2025.09
74
72
-0.02
PC*
Model=Gemma2-it
2025.09
56
7
0.45
PC*
Model=TinyLlama-chat
2025.09
54
2
0.49
PC*
Model=Deepseek-d-qwen
2025.09
45
1
0.42
PCG
Model=Deepseek-d-qwen
2025.09
13
0
0.11
Feedback
Search any
task
Search any
task
