List your company

Multi-agent debate on Mixed regime

72.4AccuracyFlat
66.88868.31969.7571.181Jun 17, 2026

Evaluation results

MethodLinks
FlatModel=gpt-oss-120b2026.0672.4
MADModel=gpt-oss-120b2026.0672.2
Transformational leadership controllerModel=gpt-oss-120b2026.0671.8
Situational leadership controllerModel=gpt-oss-120b2026.0671.6
R0-voteModel=gpt-oss-120b2026.0671.3
MADModel=llama-4-scout2026.0671.3
FlatModel=llama-4-scout2026.0671.1
Situational leadership controllerModel=llama-4-scout2026.0670.7
Transformational leadership controllerModel=llama-4-scout2026.0669.6
Situational leadership controllerModel=gemma-4-31B-it2026.0669.6
R0-voteModel=llama-4-scout2026.0669.3
Transformational leadership controllerModel=gemma-4-31B-it2026.0669.1
MADModel=gemma-4-31B-it2026.0668
R0-voteModel=gemma-4-31B-it2026.0667.8
FlatModel=gemma-4-31B-it2026.0667.1