Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on PIQA In-Domain (Accuracy)
Loading...
89
Accuracy
Few-shot*
62.376
69.288
76.2
83.112
Sep 26, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Few-shot*
Model=Qwen3-32B
2025.09
89
Few-shot*
Model=Llama3.1-70B
2025.09
88.6
ICR
Model=Llama3.1-70B
2025.09
83.2
ICR
Model=Qwen3-32B
2025.09
82.8
Zero-shot
Model=Qwen3-32B
2025.09
78
I2CL
Model=Llama3.1-70B
2025.09
75.4
I2CL
Model=Qwen3-32B
2025.09
74.2
FV
Model=Llama3.1-70B
2025.09
71.2
Zero-shot
Model=Llama3.1-70B
2025.09
70.4
FV
Model=Qwen3-32B
2025.09
63.4
Feedback
Search any
task
Search any
task
