Overall score
3.004
95% CI [2.974, 3.034]
Based on 4,531 sessions
Rank 12 of 13 models on the Chinese leaderboard
4 aspects
● Conversational ability 0%3.87
● Character consistency 100%3.00
● Role-playing attractiveness 0%3.26
● Personality back-testing 0%—
13 dimensions
- Fluency
- 3.66
- Coherency
- 4.01
- Consistency
- 3.92
- Knowledge exposure
- 2.28
- Knowledge accuracy
- 3.05
- Knowledge hallucination
- 3.06
- Persona behavior
- 3.41
- Persona utterance
- 3.23
- Human-likeness
- 3.81
- Communication skills
- 3.15
- Expression diversity
- 2.95
- Empathy
- 3.13
- 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 | 12 / 13 | 3.00 | 3.0 – 3.0 | 3.9 | 3.0 | 3.3 | — | 4,531 |