Overall score
3.251
95% CI [3.227, 3.272]
Based on 4,531 sessions
Rank 7 of 13 models on the Chinese leaderboard
4 aspects
● Conversational ability 0%4.11
● Character consistency 100%3.25
● Role-playing attractiveness 0%3.57
● Personality back-testing 0%—
13 dimensions
- Fluency
- 3.87
- Coherency
- 4.24
- Consistency
- 4.22
- Knowledge exposure
- 2.30
- Knowledge accuracy
- 3.14
- Knowledge hallucination
- 3.29
- Persona behavior
- 4.07
- Persona utterance
- 3.45
- Human-likeness
- 4.06
- Communication skills
- 3.38
- Expression diversity
- 3.61
- Empathy
- 3.25
- 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 | 7 / 13 | 3.25 | 3.2 – 3.3 | 4.1 | 3.3 | 3.6 | — | 4,531 |