HyperAI超神経

プラットフォーム

Bias Detection On Rt Inod Bias

評価指標

Best-of

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

		Paper Title
GPT-4	0.5	Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations
Gemma	0.41	Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations
Baseline	0.41	Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations
Mistral	0.36	Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations
Llama2	0.34	Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations

0 of 5 row(s) selected.

Bias Detection On Rt Inod Bias | SOTA | HyperAI超神経