Overall score
3.063
95% CI [3.033, 3.093]
Based on 4,530 sessions
Rank 11 of 13 models on the Chinese leaderboard
4 aspects
● Conversational ability 0%3.65
● Character consistency 100%3.06
● Role-playing attractiveness 0%3.29
● Personality back-testing 0%—
13 dimensions
- Fluency
- 3.53
- Coherency
- 3.85
- Consistency
- 3.58
- Knowledge exposure
- 2.54
- Knowledge accuracy
- 3.08
- Knowledge hallucination
- 3.07
- Persona behavior
- 3.51
- Persona utterance
- 3.12
- Human-likeness
- 3.38
- Communication skills
- 3.53
- Expression diversity
- 3.00
- Empathy
- 3.26
- MBTI accuracy
- —
Scores by language
Tested November 1, 2026| Language | Rank | Overall | 95% confidence interval | Conversational ability | Character consistency | Role-playing attractiveness | Personality back-testing | Sessions |
|---|---|---|---|---|---|---|---|---|
| Chinese | 11 / 13 | 3.06 | 3.0 – 3.1 | 3.6 | 3.1 | 3.3 | — | 4,530 |