Our new X account is live! Follow @wizwand_team for updates

NLG Evaluation on HelpSteer2

0.65Spearman Correlation

Qwen

Updated 4d ago

Evaluation Results

Method	Links
Qwen 2026.02		0.65
Qwen 2026.02		0.63
Mixtral 2026.02		0.61
GPT-4o-mini 2026.02		0.58
GPT-4o 2026.02		0.56
Mixtral 2026.02		0.5
GPT-4o 2026.02		0.49
GPT-4o-mini 2026.02		0.47
Llama 2026.02		0.43
Llama 2026.02		0.31