List your company

Social reasoning on Social regime (n = 300)

51.3Exact Match AccuracySituational leadership
36.7440.5244.348.08Jun 17, 2026

Evaluation results

MethodLinks
Situational leadershipModel=llama-4-scout2026.0651.3
Transformational leadershipModel=llama-4-scout2026.0648.3
Theory-free controlModel=llama-4-scout2026.0646.7
directives-only ablationModel=llama-4-scout2026.0645.3
Situational leadershipModel=gpt-oss-120b2026.0645
FlatModel=llama-4-scout2026.0643.3
Transformational leadershipModel=gpt-oss-120b2026.0643
Transactional leadershipModel=llama-4-scout2026.0643
accept-only ablationModel=llama-4-scout2026.0642.7
Theory-free controlModel=gpt-oss-120b2026.0642.3
Transactional leadershipModel=gpt-oss-120b2026.0642.3
accept-only ablationModel=gpt-oss-120b2026.0642.3
directives-only ablationModel=gpt-oss-120b2026.0642
FlatModel=gpt-oss-120b2026.0641.7
Transformational leadershipModel=gemma-4-31B-it2026.0639.7
Theory-free controlModel=gemma-4-31B-it2026.0639
Transactional leadershipModel=gemma-4-31B-it2026.0638.7
accept-only ablationModel=gemma-4-31B-it2026.0638.7
FlatModel=gemma-4-31B-it2026.0638.3
Situational leadershipModel=gemma-4-31B-it2026.0638
directives-only ablationModel=gemma-4-31B-it2026.0637.3