Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Cultural Reasoning on BLEnD (test)
Loading...
85.81
Accuracy
C-Mining
73.9748
77.0474
80.12
83.1926
Apr 17, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
C-Mining
Backbone=Qwen3-32B, In...
2026.04
85.81
Qwen3-32B
Backbone=Qwen3-32B, In...
2026.04
82.63
C-Mining
Backbone=Qwen2.5-7B, I...
2026.04
80.94
CultureSPA
Backbone=Qwen2.5-7B, I...
2026.04
78.69
Llama3.1-8B
Backbone=Llama3.1-8B,...
2026.04
77.88
CultureBank
Backbone=Qwen2.5-7B, I...
2026.04
77.75
Qwen2.5-7B
Backbone=Qwen2.5-7B, I...
2026.04
77.12
Ministral3-8B
Backbone=Ministral3-8B...
2026.04
76.52
CultureLLM
Backbone=Qwen2.5-7B, I...
2026.04
74.75
GLM4-9B
Backbone=GLM4-9B, Inst...
2026.04
74.43
Feedback
Search any
task
Search any
task