Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Algebraic Reasoning on AQUA (test)
Loading...
30.94
Accuracy
Interaction-Aware Influence Function (Ours)
7.5296
13.6073
19.685
25.7627
May 15, 2026
Accuracy
Updated 16d ago
Evaluation Results
Method
Method
Links
Accuracy
Interaction-Aware Influence Function (Ours)
Base Model=Llama-3.1-8...
2026.05
30.94
Random
Base Model=Llama-3.1-8...
2026.05
24.65
RDS+
Base Model=Llama-3.1-8...
2026.05
24.65
Additive IF
Base Model=Llama-3.1-8...
2026.05
20.63
LESS
Base Model=Llama-3.1-8...
2026.05
8.82
NV-Embed
Base Model=Llama-3.1-8...
2026.05
8.43
Feedback
Search any
task
Search any
task