Truthfulqa
Metrics
% info
% true
% true (gpt-judge)
bleu
bleurt
llm_model
mc1
mc2
model_url
organization
parameters
release_date
rouge
updated_time
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | % info | % true | % true (gpt-judge) | bleu | bleurt | llm_model | mc1 | mc2 | model_url | organization | parameters | release_date | rouge | updated_time |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Model 1 | 97.55 | 20.44 | 20.56 | -17.18 | -0.54 | GPT-3 175B | 0.21 | 0.33 | https://openai.com/index/gpt-3-apps/ | OpenAI | 175B | 2020.5.28 | -17.17 | 2022.5.8 |