Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Cultural Reasoning on SAGE (test)
Loading...
97.57
Accuracy
C-Mining
79.0996
83.8948
88.69
93.4852
Apr 17, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
C-Mining
Backbone=Qwen3-32B, In...
2026.04
97.57
C-Mining
Backbone=Qwen2.5-7B, I...
2026.04
96.59
CultureBank
Backbone=Qwen2.5-7B, I...
2026.04
96.23
Qwen3-32B
Backbone=Qwen3-32B, In...
2026.04
95.01
Qwen2.5-7B
Backbone=Qwen2.5-7B, I...
2026.04
93.19
CultureSPA
Backbone=Qwen2.5-7B, I...
2026.04
92.46
CultureLLM
Backbone=Qwen2.5-7B, I...
2026.04
90.02
Llama3.1-8B
Backbone=Llama3.1-8B,...
2026.04
89.66
GLM4-9B
Backbone=GLM4-9B, Inst...
2026.04
86.98
Ministral3-8B
Backbone=Ministral3-8B...
2026.04
79.81
Feedback
Search any
task
Search any
task