ResearchBenchmarksMathematical Reasoning on AIME24 (Avg@16)Follow14.4Avg@16 ScoreDr.GRPO3.3766.2389.111.962May 8, 2026Evaluation ResultsMethodMethodLinksAvg@16 ScoreDr.GRPOBackbone=Llama3.2-3B-I...Backbone=Llama3.2-3B-Instruct, Domain Type=In-domain2026.0514.4GRPOBackbone=Llama3.2-3B-I...Backbone=Llama3.2-3B-Instruct, Domain Type=In-domain2026.0513.8PRIMEBackbone=Llama3.2-3B-I...Backbone=Llama3.2-3B-Instruct, Domain Type=In-domain2026.0512.1OriginalBackbone=Llama3.2-3B-I...Backbone=Llama3.2-3B-Instruct, Domain Type=In-domain2026.053.8