List your company

Cultural Reasoning on SAGE (test)

97.57AccuracyC-Mining
79.099683.894888.6993.4852Apr 17, 2026

Evaluation results

MethodLinks
C-MiningBackbone=Qwen3-32B, Instruction Tuning Method=C-Mining2026.0497.57
C-MiningBackbone=Qwen2.5-7B, Instruction Tuning Method=C-Mining2026.0496.59
CultureBankBackbone=Qwen2.5-7B, Instruction Tuning Method=CultureBank2026.0496.23
Qwen3-32BBackbone=Qwen3-32B, Instruction Tuning Method=Standard2026.0495.01
Qwen2.5-7BBackbone=Qwen2.5-7B, Instruction Tuning Method=Standard2026.0493.19
CultureSPABackbone=Qwen2.5-7B, Instruction Tuning Method=CultureSPA2026.0492.46
CultureLLMBackbone=Qwen2.5-7B, Instruction Tuning Method=CultureLLM2026.0490.02
Llama3.1-8BBackbone=Llama3.1-8B, Instruction Tuning Method=Standard2026.0489.66
GLM4-9BBackbone=GLM4-9B, Instruction Tuning Method=Standard2026.0486.98
Ministral3-8BBackbone=Ministral3-8B, Instruction Tuning Method=Standard2026.0479.81