Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-form Question Answering with Citations on ELI5
Loading...
0.186
Correctness
ChatGPT Inline Search
0.03312
0.07281
0.1125
0.15219
Apr 4, 2024
Correctness
Attribution
Updated 1mo ago
Evaluation Results
Method
Method
Links
Correctness
Attribution
ChatGPT Inline Search
Base Model=ChatGPT, Pi...
2024.04
0.186
0.446
ChatGPT Closed Book
Base Model=ChatGPT, Pi...
2024.04
0.186
0.155
ChatGPT Snippet
Base Model=ChatGPT, Pi...
2024.04
0.143
0.475
ChatGPT Summarization
Base Model=ChatGPT, Pi...
2024.04
0.123
0.498
ChatGPT Vanilla
Base Model=ChatGPT, Pi...
2024.04
0.12
0.505
Vicuna-13B Vanilla
Base Model=Vicuna-13B,...
2024.04
0.1
0.174
LongT5 3B +Blueprint +Attribution
Base Model=LongT5 3B,...
2024.04
0.052
0.609
LLaMA-13B Vanilla
Base Model=LLaMA-13B,...
2024.04
0.039
0.039
Feedback
Search any
task
Search any
task