List your company

Machine Learning Engineering on MLE-bench-30 (test)

76Percentile RankAIRA2
38.0447.89557.7567.605Mar 27, 2026

Evaluation results

MethodLinks
AIRA2Time budget=72h, Number of GPUs=8, Subagents=true, Hidden Consistent Eval (HCE)=true, Evolution=true2026.037661.158.936.7
AIRA2 (No Subagents)Time budget=72h, Number of GPUs=8, Subagents=false, Hidden Consistent Eval (HCE)=true, Evolution=true2026.0373.76053.337.8
AIRA2Time budget=24h, Number of GPUs=8, Subagents=true, Hidden Consistent Eval (HCE)=true, Evolution=true2026.0371.857.85032.2
MARS+Time budget=24h, Number of GPUs=22026.0369.964.451.124.4
FM-Agent 2.0Time budget=24h, Number of GPUs=12026.0369.661.157.836.7
AIRA2 (No Subagents)Time budget=24h, Number of GPUs=8, Subagents=false, Hidden Consistent Eval (HCE)=true, Evolution=true2026.0368.652.247.832.2
AIRA2 (No Evo.)Time budget=72h, Number of GPUs=8, Subagents=true, Hidden Consistent Eval (HCE)=true, Evolution=false2026.0365.247.143.524.7
MLEvolveTime budget=24h, Number of GPUs=12026.0364.157.852.222.2
AIRA2 (No Evo.)Time budget=24h, Number of GPUs=8, Subagents=true, Hidden Consistent Eval (HCE)=true, Evolution=false2026.036445.94023.5
AIRA2 (1 GPU)Time budget=72h, Number of GPUs=1, Subagents=true, Hidden Consistent Eval (HCE)=true, Evolution=true2026.0363.551.141.124.4
MARSTime budget=24h, Number of GPUs=12026.0360.454.444.418.9
AIRA2Time budget=3h, Number of GPUs=8, Subagents=true, Hidden Consistent Eval (HCE)=true, Evolution=true2026.0359.938.933.320
ML-Master 2.0Time budget=24h, Number of GPUs=22026.0357.652.2408.9
AIRA2 (1 GPU)Time budget=24h, Number of GPUs=1, Subagents=true, Hidden Consistent Eval (HCE)=true, Evolution=true2026.0356.841.132.220
AIRA2 (No HCE)Time budget=24h, Number of GPUs=8, Subagents=true, Hidden Consistent Eval (HCE)=false, Evolution=true2026.0356.846.545.530.7
AIRA2 (No HCE)Time budget=72h, Number of GPUs=8, Subagents=true, Hidden Consistent Eval (HCE)=false, Evolution=true2026.0356.347.546.532.7
AIRA2 (No Evo.)Time budget=3h, Number of GPUs=8, Subagents=true, Hidden Consistent Eval (HCE)=true, Evolution=false2026.0354.735.331.816.5
AIRA2 (No Subagents)Time budget=3h, Number of GPUs=8, Subagents=false, Hidden Consistent Eval (HCE)=true, Evolution=true2026.0354.433.33013.3
PiEvolveTime budget=24h, Number of GPUs=12026.0354.154.45027.8
AIRA2 (No HCE)Time budget=3h, Number of GPUs=8, Subagents=true, Hidden Consistent Eval (HCE)=false, Evolution=true2026.0343.429.725.712.9
AIRA2 (1 GPU)Time budget=3h, Number of GPUs=1, Subagents=true, Hidden Consistent Eval (HCE)=true, Evolution=true2026.0341.322.217.810
AIRA-dojoTime budget=24h, Number of GPUs=12026.0339.525.820.58.8