OpenESM: Energy-Steered Models Are Scalable Foundation Learners
Open paper
Benchmark
Model
Rank
Results
question-answering-on-boolq
OpenESM FineWeb d26
#109
Accuracy: 57.83
common-sense-reasoning-on-winogrande
OpenESM DCLM d26
#141
Accuracy: 56.35
question-answering-on-piqa
OpenESM FineWeb d26
#155
Accuracy: 70.02
Rank counts only results with a code link.