List your company

Roleplay Simulation on SimArena Math

71.5Primary MetricGemini 3.1 Pro
65.98867.41968.8570.281Jun 12, 2026

Evaluation results

MethodLinks
Gemini 3.1 Pro2026.0671.5
Qwen 3.6 Plus2026.0670.9
OSIM 8BModel=OSIM, Parameter Count=8B, Training Stage=Final2026.0670.7
Others *2026.0670.5
Qwen3 8B InstModel=Qwen3-8B-Instruct, Parameter Count=8B2026.0668.9
Claude Opus 4.72026.0668.7
GPT 5.52026.0668.5
OSIM 8B-MidModel=OSIM, Parameter Count=8B, Training Stage=Mid-trained2026.0668.1
Base 8BModel=Qwen3-8B-Base, Parameter Count=8B2026.0666.2