Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Poem Sentiment Analysis on PoemS (val)
Loading...
68.4
Accuracy
IA2 → SFT
49.16
54.155
59.15
64.145
Sep 26, 2025
Accuracy
ECE
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
ECE
IA2 → SFT
Model=Qwen3-4B-Base, N...
2025.09
68.4
0.3
ICL
Model=Qwen3-4B-Base, N...
2025.09
65.1
0.11
IA2 only
Model=Qwen3-4B-Base, N...
2025.09
62.4
0.19
IA2 → SFT
Model=Qwen3-4B-Base, N...
2025.09
60.6
0.36
ICL
Model=Qwen3-4B-Base, N...
2025.09
56.9
0.12
SFT only
Model=Qwen3-4B-Base, N...
2025.09
56.5
0.33
IA2 only
Model=Qwen3-4B-Base, N...
2025.09
52.8
0.15
SFT only
Model=Qwen3-4B-Base, N...
2025.09
49.9
0.48
Feedback
Search any
task
Search any
task