BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
Open paper
Benchmark
Model
Rank
Results
mathematical-reasoning-on-aime24
BeamPERL (best-performing checkpoint)
#94
Acc: 40.0
mathematical-reasoning-on-aime-2025
BeamPERL (best-performing checkpoint)
#120
Accuracy: 23.3
Rank counts only results with a code link.