List your company

Word Reasoning on Acronym (4,5) (OOD)

12.3AccuracyBOLT -> GRPO
2.6285.1397.6510.161Dec 3, 2025

Evaluation results

MethodLinks
BOLT -> GRPObase_model=Qwen2.5-1.5B-Instruct, training=SFT + GRPO2025.1212.3
SkillFactory -> GRPObase_model=Qwen2.5-1.5B-Instruct, training=SFT + GRPO2025.1212.1
STaR -> GRPObase_model=Qwen2.5-1.5B-Instruct, training=SFT + GRPO2025.129.8
R1 Distillbase_model=Qwen2.5-1.5B-Instruct, training=SFT2025.129.4
RL-Onlybase_model=Qwen2.5-1.5B-Instruct, training=RL2025.128.7
Qwen2.5 1.5B Instructbase_model=Qwen2.5-1.5B-Instruct, training=None2025.126.9
BOLTbase_model=Qwen2.5-1.5B-Instruct, training=SFT2025.126.2
R1 Distill -> GRPObase_model=Qwen2.5-1.5B-Instruct, training=SFT + GRPO2025.126
STaRbase_model=Qwen2.5-1.5B-Instruct, training=SFT2025.124
SkillFactorybase_model=Qwen2.5-1.5B-Instruct, training=SFT2025.123