Persona Simulation on TwinVoice
86AccuracyGemini 3.1 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3.1 Pro2026.06 | 86 | |
| Claude Opus 4.72026.06 | 83 | |
| GPT 5.52026.06 | 74 | |
| Qwen 3.6 Plus2026.06 | 71 | |
| OSIM 8BModel=OSIM, Parameter Count=8B, Training Stage=Final2026.06 | 68 | |
| GPT-5.42026.05 | 64 | |
| DITTOBackbone=Qwen3-VL-8B-Instruct2026.05 | 61 | |
| GRPOBackbone=Qwen3-VL-8B-Instruct2026.05 | 47 | |
| Qwen3-VL-8B-InstructRole=Base2026.05 | 43 | |
| Qwen3 8B InstModel=Qwen3-8B-Instruct, Parameter Count=8B2026.06 | 42 | |
| Others *2026.06 | 40 | |
| HER-32B2026.05 | 39 | |
| OSIM 8B-MidModel=OSIM, Parameter Count=8B, Training Stage=Mid-trained2026.06 | 25 | |
| GPT-5-nano2026.05 | 23 | |
| Base 8BModel=Qwen3-8B-Base, Parameter Count=8B2026.06 | 19 |