Conversation Simulation on Humanual-Chat
28.2Primary Quality ScoreGPT 5.5
Evaluation results
| Method | Links | |
|---|---|---|
| GPT 5.52026.06 | 28.2 | |
| OSIM 8BModel=OSIM, Parameter Count=8B, Training Stage=Final2026.06 | 28.2 | |
| Others *2026.06 | 25.8 | |
| Qwen3 8B InstModel=Qwen3-8B-Instruct, Parameter Count=8B2026.06 | 24.7 | |
| Claude Opus 4.72026.06 | 22.6 | |
| Qwen 3.6 Plus2026.06 | 22.2 | |
| Gemini 3.1 Pro2026.06 | 21 | |
| Base 8BModel=Qwen3-8B-Base, Parameter Count=8B2026.06 | 12 | |
| OSIM 8B-MidModel=OSIM, Parameter Count=8B, Training Stage=Mid-trained2026.06 | 7.8 |