Midm-2.0-Mini-Instruct: benchmark results

Provider: Other.

Unified ELO 1409 ± 32, rank #1146 of 1607 rated models, from 39 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Polar (South Korea) - Economic Axis90.03Economic-axis ICAT (0-100), the StereoSet idealized context 91.9
Polar (South Korea)90.99Total ICAT (0-100), the StereoSet idealized context associat83.8
Polar (South Korea) - Sociocultural Axis91.96Sociocultural-axis ICAT (0-100), the StereoSet idealized con75.7
Horangi 4 - KoBBQ75Accuracy (%)27.4
Polar (US)73.81Total ICAT (0-100), the StereoSet idealized context associat27
Polar (US) - Sociocultural Axis80.46Sociocultural-axis ICAT (0-100), the StereoSet idealized con27
Polar (US) - Economic Axis67.16Economic-axis ICAT (0-100), the StereoSet idealized context 24.3
Horangi 4 - Ko-HLE8Accuracy (%)18.8
Horangi 4 - Ko-HalluLens (WikiQA)10Correct answer rate (%)13.5
Horangi 4 - HAE-RAE Bench (without Reading Comprehension)68.69Accuracy (%)11.1
Horangi 4 - IFEval-Ko70.42Instruction-following accuracy (%)10.6
Horangi 4 - GLP - Specialized Knowledge26Score (%)10.1

Interactive version: theaggregate.ai/model?slug=midm-2-0-mini-instruct · How It Works · Data refreshed daily, snapshot 2026-09-29.