Overall score
3.100
95% CI [3.070, 3.132]
Based on 4,531 sessions
Rank 10 of 13 models on the Chinese leaderboard
4 aspects
● Conversational ability 0%4.10
● Character consistency 100%3.10
● Role-playing attractiveness 0%3.41
● Personality back-testing 0%—
13 dimensions
- Fluency
- 3.91
- Coherency
- 4.22
- Consistency
- 4.17
- Knowledge exposure
- 2.30
- Knowledge accuracy
- 3.14
- Knowledge hallucination
- 3.25
- Persona behavior
- 3.45
- Persona utterance
- 3.35
- Human-likeness
- 4.04
- Communication skills
- 3.42
- Expression diversity
- 2.90
- Empathy
- 3.29
- 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 | 10 / 13 | 3.10 | 3.1 – 3.1 | 4.1 | 3.1 | 3.4 | — | 4,531 |