List your company

Mathematical Reasoning on MATH (Pass@1, Pass@2)

88.42Pass@1Phi-4-mini + Mistral3-3B
52.841662.078371.31580.5517Jan 29, 2026

Evaluation results

MethodLinks
Phi-4-mini + Mistral3-3BTraining Framework=CORE, Model Configuration=Team2026.0188.4292.08
Phi-4-mini-reasoningTraining Framework=CORE, Model Configuration=Single2026.0185.2490.01
Mistral3-3B-ReasoningTraining Framework=CORE, Model Configuration=Single2026.0183.7289.12
Phi-4-mini + Mistral3-3B + OracleTraining Framework=SD-E2, Model Configuration=Oracle2026.0171.8577.7
Phi-4-mini-reasoningTraining Framework=SD-E2, Model Configuration=Single2026.0169.6873.82
Mistral3-3B-ReasoningTraining Framework=SD-E2, Model Configuration=Single2026.0167.2573.15
Phi-4-mini + Mistral3-3B + OracleTraining Framework=Base, Model Configuration=Oracle2026.0159.2570.7
Phi-4-mini-reasoningTraining Framework=Base, Model Configuration=Single2026.0157.0468.16
Mistral3-3B-ReasoningTraining Framework=Base, Model Configuration=Single2026.0154.2164.44