Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Chunking on Chunk
Loading...
61.84
F1
Per-Span Majority
-2.4736
14.2232
30.92
47.6168
Nov 15, 2022
F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1
Per-Span Majority
2022.11
61.84
GPT-Neo
Model Size=20B, k=10
2022.11
57.6
GPT-Neo
Model Size=20B, k=9
2022.11
54.84
GPT-Neo
Model Size=20B, k=7
2022.11
54
GPT-Neo
Model Size=2.7B, k=10
2022.11
53.18
GPT-Neo
Model Size=20B, k=5
2022.11
50.98
GPT-Neo
Model Size=20B, k=3
2022.11
48.33
GPT-Neo
Model Size=6B, k=10
2022.11
39.63
GPT-Neo
Model Size=1.3B, k=10
2022.11
37.56
GPT-Neo
Model Size=125M, k=10
2022.11
36.85
GPT-Neo
Model Size=20B, k=1
2022.11
32.02
GPT-Neo
Model Size=20B, k=0
2022.11
1.08
Majority Label
2022.11
0
Feedback
Search any
task
Search any
task
