Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Classification on GoEmotions (Accuracy and Macro-F1)
Loading...
81.63
Accuracy
slm-judge
44.5436
54.1718
63.8
73.4282
Apr 1, 2026
Accuracy
Macro-F1
Updated 2mo ago
Evaluation Results
Method
Method
Links
Accuracy
Macro-F1
slm-judge
2026.04
81.63
63.8
slm-judge
Dropout=p = 0.1
2026.04
79.37
49.98
slm-judge
Training Strategy=Earl...
2026.04
79.17
56.85
slm-judge
Training Strategy=Full...
2026.04
78.19
49.67
GPT-5-nano
Evaluation Protocol=Ze...
2026.04
51.77
39.69
GPT-5.2-chat
Evaluation Protocol=Ze...
2026.04
50.62
40.99
GPT-5.2-chat
Evaluation Protocol=Fe...
2026.04
49.9
39.26
GPT-4o
Evaluation Protocol=Ze...
2026.04
47.41
37.32
GPT-5-mini-2025-08-07
Evaluation Protocol=Ze...
2026.04
47.32
38.75
GPT-4o
Evaluation Protocol=Fe...
2026.04
45.97
23.09
Feedback
Search any
task
Search any
task