List your company

Roleplay Simulation on Humanual Politics

43.5Primary MetricClaude Opus 4.7
14.27621.86329.4537.037Jun 12, 2026

Evaluation results

MethodLinks
Claude Opus 4.72026.0643.5
GPT 5.52026.0642
OSIM 8BModel=OSIM, Parameter Count=8B, Training Stage=Final2026.0641.9
Others *2026.0634.2
Qwen3 8B InstModel=Qwen3-8B-Instruct, Parameter Count=8B2026.0633.2
Gemini 3.1 Pro2026.0632.5
Qwen 3.6 Plus2026.0631.6
Base 8BModel=Qwen3-8B-Base, Parameter Count=8B2026.0617.8
OSIM 8B-MidModel=OSIM, Parameter Count=8B, Training Stage=Mid-trained2026.0615.4