Dialogue Understanding on rt-inod-jailbreaking

Metric: Best-of (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Best-of▼	Extra Data	Paper	Date↕	Code
1	Baseline	0.92	No	Benchmarking Llama2, Mistral, Gemma and GPT for ...	2024-04-15	Code
2	GPT-4	0.91	No	Benchmarking Llama2, Mistral, Gemma and GPT for ...	2024-04-15	Code
3	Gemma	0.91	No	Benchmarking Llama2, Mistral, Gemma and GPT for ...	2024-04-15	Code
4	Mistral	0.87	No	Benchmarking Llama2, Mistral, Gemma and GPT for ...	2024-04-15	Code
5	Llama2	0.86	No	Benchmarking Llama2, Mistral, Gemma and GPT for ...	2024-04-15	Code

#1BaselineSOTA
0.92
Best-of· 2024-04-15
Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations Code
#2GPT-4
0.91
Best-of· 2024-04-15
Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations Code
#3Gemma
0.91
Best-of· 2024-04-15
Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations Code
#4Mistral
0.87
Best-of· 2024-04-15
Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations Code
#5Llama2
0.86
Best-of· 2024-04-15
Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations Code