ResearchBenchmarksMathematical Reasoning on LiveMathBench v202505Follow6.8Avg@4GRPO2.123.3354.555.765May 8, 2026Evaluation ResultsMethodMethodLinksAvg@4GRPOBackbone=Llama3.2-3B-I...Backbone=Llama3.2-3B-Instruct, Domain Type=In-domain2026.056.8Dr.GRPOBackbone=Llama3.2-3B-I...Backbone=Llama3.2-3B-Instruct, Domain Type=In-domain2026.056.5PRIMEBackbone=Llama3.2-3B-I...Backbone=Llama3.2-3B-Instruct, Domain Type=In-domain2026.055.4OriginalBackbone=Llama3.2-3B-I...Backbone=Llama3.2-3B-Instruct, Domain Type=In-domain2026.052.3