Share your thoughts, 1 month free Claude Pro on usSee more

NLG Meta-evaluation on CUS-QA en cs

0.73Kendall Correlation

Llama 4 Scout

Updated 1mo ago

Evaluation Results

Method	Links
Llama 4 Scout 2026.03		0.73
Qwen 3 30B 2026.03		0.725
Llama 4 Scout 2026.03		0.656
Qwen 3 30B 2026.03		0.651
Llama 3.3 70B 2026.03		0.619
Llama 3.3 70B 2026.03		0.524