Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Logical Reasoning on Logic
Loading...
68.07
Accuracy
EpiCoDe
52.0644
56.2197
60.375
64.5303
Jun 4, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
EpiCoDe
Backbone=Qwen2-7B-Inst...
2025.06
68.07
ME
Backbone=Qwen2-7B-Inst...
2025.06
67.6
CD
Backbone=Qwen2-7B-Inst...
2025.06
67.43
Finetune
Backbone=Qwen2-7B-Inst...
2025.06
66.67
EpiCoDe
Backbone=Deepseek-7B-Chat
2025.06
59.05
ME
Backbone=Deepseek-7B-Chat
2025.06
58.89
CD
Backbone=Deepseek-7B-Chat
2025.06
58.46
EpiCoDe
Backbone=Llama-3.2-3B-...
2025.06
57.48
Finetune
Backbone=Deepseek-7B-Chat
2025.06
57.22
CD
Backbone=Llama-3.2-3B-...
2025.06
56.62
ME
Backbone=Llama-3.2-3B-...
2025.06
55.11
EpiCoDe
Backbone=Qwen2-1.5B-In...
2025.06
53.87
ME
Backbone=Qwen2-1.5B-In...
2025.06
53.63
Finetune
Backbone=Llama-3.2-3B-...
2025.06
53.45
CD
Backbone=Qwen2-1.5B-In...
2025.06
53.42
Finetune
Backbone=Qwen2-1.5B-In...
2025.06
52.68
Feedback
Search any
task
Search any
task