Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Downstream evaluation on 9 downstream tasks
Loading...
62.6
Average Accuracy
Surefire-3B
54.592
56.671
58.75
60.829
Oct 21, 2025
Average Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Accuracy
Surefire-3B
d_model=4096, f_size=4...
2025.10
62.6
Panda-3B
d_model=4096, f_size=4...
2025.10
62.5
LLaMA-3.2-3B
d_model=3072, f_size=8...
2025.10
61.9
Panda-1B
d_model=2560, f_size=4...
2025.10
57
Surefire-1B
d_model=2560, f_size=6...
2025.10
55.4
LLaMA-3.2-1B
d_model=2048, f_size=8...
2025.10
54.9
Feedback
Search any
task
Search any
task