List your company

Social Skill Simulation on Sotopia Hard

49.2Primary MetricOSIM 8B
20.28827.79435.342.806Jun 12, 2026

Evaluation results

MethodLinks
OSIM 8BModel=OSIM, Parameter Count=8B, Training Stage=Final2026.0649.2
OSIM 8B-MidModel=OSIM, Parameter Count=8B, Training Stage=Mid-trained2026.0645.6
Claude Opus 4.72026.0632.4
GPT 5.52026.0631.9
Others *2026.0631.7
Qwen 3.6 Plus2026.0628.3
Gemini 3.1 Pro2026.0627.8
Qwen3 8B InstModel=Qwen3-8B-Instruct, Parameter Count=8B2026.0627.7
Base 8BModel=Qwen3-8B-Base, Parameter Count=8B2026.0621.4