Conversation Simulation on SimArena Doc
84.1Primary MetricOSIM 8B
Evaluation Results
| Method | Links | |
|---|---|---|
| OSIM 8BModel=OSIM, Parameter Count=8B, Training Stage=Final2026.06 | 84.1 | |
| Qwen3 8B InstModel=Qwen3-8B-Instruct, Parameter Count=8B2026.06 | 83.6 | |
| Claude Opus 4.72026.06 | 83.5 | |
| Others *2026.06 | 83.5 | |
| GPT 5.52026.06 | 83.4 | |
| Gemini 3.1 Pro2026.06 | 83 | |
| Qwen 3.6 Plus2026.06 | 82.4 | |
| OSIM 8B-MidModel=OSIM, Parameter Count=8B, Training Stage=Mid-trained2026.06 | 80.3 | |
| Base 8BModel=Qwen3-8B-Base, Parameter Count=8B2026.06 | 79.6 |