List your company
ResearchFormerly WizWand

Open-QA Evaluation on EVOUNA-NaturalQuestions

97.9F1 ScoreAnother Human
76.47682.03887.693.162May 26, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Another HumanQA System=GPT-42024.0597.996.6
Another HumanQA System=InstructGPT2024.0597.896.8
Another HumanQA System=DPR-FiD2024.0597.496.3
Another HumanQA System=BingChat2024.0597.295.5
Another HumanQA System=ChatGPT2024.0596.595.6
GPT-3.5 (best prompting)QA System=DPR-FiD2024.0595.593.9
GPT-3.5QA System=DPR-FiD2024.0595.393.6
EntailmentQA System=DPR-FiD2024.0594.892.5
EntailmentQA System=GPT-42024.0593.890.1
EntailmentQA System=InstructGPT2024.0592.790.2
EntailmentQA System=ChatGPT2024.0592.688.9
EntailmentQA System=BingChat2024.0592.688.1
Lexical MatchQA System=DPR-FiD2024.059289.7
Entailment (small)QA System=DPR-FiD2024.0591.588.5
GPT-3.5 (best prompting)QA System=GPT-42024.0591.286
Entailment (small)QA System=GPT-42024.0589.985
GPT-3.5 (best prompting)QA System=ChatGPT2024.0589.484.5
GPT-3.5 (best prompting)QA System=InstructGPT2024.0588.384.5
Entailment (small)QA System=InstructGPT2024.058885.4
Lexical MatchQA System=BingChat2024.0587.882.3
Entailment (small)QA System=BingChat2024.0587.882
Entailment (small)QA System=ChatGPT2024.0587.783.2
Lexical MatchQA System=GPT-42024.0587.682.5
GPT-3.5QA System=InstructGPT2024.0587.284.1
GPT-3.5 (best prompting)QA System=BingChat2024.0587.180.4
Lexical MatchQA System=InstructGPT2024.0586.984.8
GPT-3.5QA System=ChatGPT2024.0586.982.2
GPT-3.5QA System=GPT-42024.0586.880.9
Lexical MatchQA System=ChatGPT2024.058580.3
BERTScoreQA System=GPT-42024.0584.376
BERTScoreQA System=DPR-FiD2024.0583.575.1
BERTScoreQA System=ChatGPT2024.0581.272.8
BERTScoreQA System=InstructGPT2024.0577.669.5
BERTScoreQA System=BingChat2024.0577.567.5
GPT-3.5QA System=BingChat2024.0577.369.5