List your company

Mathematical Problem Solving on MATH-500 simple-numeric-answer (Level 5)

96AccuracyFlat
65.21673.20881.289.192Jun 17, 2026

Evaluation results

MethodLinks
FlatModel=gpt-oss-120b2026.069694.762.51.24
Theory-free controlModel=gpt-oss-120b2026.0694.494.3501.32
FlatModel=gemma-4-31B-it2026.0694.479.275.91.58
Transactional leadershipModel=gpt-oss-120b2026.0693.695.131.21.17
Transformational leadershipModel=gpt-oss-120b2026.0693.694.731.21.2
Situational leadershipModel=gpt-oss-120b2026.0693.695.531.21.31
Theory-free controlModel=gemma-4-31B-it2026.0691.279.261.11.72
Transactional leadershipModel=gemma-4-31B-it2026.069083.655.61.26
Transformational leadershipModel=gemma-4-31B-it2026.0686.478.442.61.42
Situational leadershipModel=gemma-4-31B-it2026.0685.677.638.91.64
FlatModel=llama-4-scout2026.0673.663.241.41.76
Transactional leadershipModel=llama-4-scout2026.067273.232.31.46
Theory-free controlModel=llama-4-scout2026.067066.828.32.03
Situational leadershipModel=llama-4-scout2026.066864.828.31.87
Transformational leadershipModel=llama-4-scout2026.0666.466.421.21.56