ResearchBenchmarksMathematical Reasoning on Minerva (mean@16)Follow40.3Mean@16IRDS26.57230.13633.737.264May 27, 2026Evaluation ResultsMethodMethodLinksMean@16IRDSModel=QWEN3-4B, Data B...Model=QWEN3-4B, Data Budget=10%2026.0540.3IRDSModel=QWEN3-1.7B, Data...Model=QWEN3-1.7B, Data Budget=10%2026.0529.7IRDSModel=LLAMA-3.1-8B-INS...Model=LLAMA-3.1-8B-INSTRUCT, Data Budget=10%2026.0527.1