Leaderboards

ClaudeClaude Opus 5.5

anthropic/claude-opus-5.5
Overall score
3.402
95% CI [3.378, 3.426]
Based on 4,531 sessions
Rank 2 of 13 models on the Chinese leaderboard
4 aspects
● Conversational ability 0%4.23
● Character consistency 100%3.40
● Role-playing attractiveness 0%3.71
● Personality back-testing 0%—
13 dimensions
Fluency
4.06
Coherency
4.31
Consistency
4.31
Knowledge exposure
2.55
Knowledge accuracy
3.25
Knowledge hallucination
3.43
Persona behavior
4.21
Persona utterance
3.57
Human-likeness
4.16
Communication skills
3.53
Expression diversity
3.79
Empathy
3.35
MBTI accuracy
—
FluencyCoherencyConsistencyKnowledge exposureKnowledge accuracyKnowledge hallucinationPersona behaviorPersona utteranceHuman-likenessCommunication skillsExpression diversityEmpathyMBTI accuracy2

Scores by language

Tested November 1, 2026
LanguageRankOverall95% confidence intervalConversational abilityCharacter consistencyRole-playing attractivenessPersonality back-testingSessions
Chinese2 / 133.403.4 – 3.44.23.43.7—4,531