ResearchBenchmarksMathematical Reasoning on AIME 24 (mean@16)Follow32.6Mean Score (@16)IRDS1.5049.57717.6525.723May 27, 2026Evaluation ResultsMethodMethodLinksMean Score (@16)IRDSModel=QWEN3-4B, Data B...Model=QWEN3-4B, Data Budget=10%2026.0532.6IRDSModel=QWEN3-1.7B, Data...Model=QWEN3-1.7B, Data Budget=10%2026.0518.3IRDSModel=LLAMA-3.1-8B-INS...Model=LLAMA-3.1-8B-INSTRUCT, Data Budget=10%2026.052.7