Overall score
3.292
95% CI [3.265, 3.317]
Based on 4,528 sessions
Rank 6 of 13 models on the Chinese leaderboard
4 aspects
● Conversational ability 0%3.88
● Character consistency 100%3.29
● Role-playing attractiveness 0%3.55
● Personality back-testing 0%—
13 dimensions
- Fluency
- 3.71
- Coherency
- 4.07
- Consistency
- 3.85
- Knowledge exposure
- 2.81
- Knowledge accuracy
- 3.26
- Knowledge hallucination
- 3.27
- Persona behavior
- 3.83
- Persona utterance
- 3.29
- Human-likeness
- 3.62
- Communication skills
- 3.75
- Expression diversity
- 3.39
- Empathy
- 3.44
- 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 | 6 / 13 | 3.29 | 3.3 – 3.3 | 3.9 | 3.3 | 3.5 | — | 4,528 |