Leaderboards

QwenQwen3.8 Max Prime

qwen/qwen3.8-max-prime
Overall score
3.324
95% CI [3.297, 3.351]
Based on 4,531 sessions
Rank 5 of 13 models on the Chinese leaderboard
4 aspects
● Conversational ability 0%4.15
● Character consistency 100%3.32
● Role-playing attractiveness 0%3.61
● Personality back-testing 0%—
13 dimensions
Fluency
3.97
Coherency
4.25
Consistency
4.25
Knowledge exposure
2.54
Knowledge accuracy
3.25
Knowledge hallucination
3.31
Persona behavior
4.02
Persona utterance
3.50
Human-likeness
4.12
Communication skills
3.42
Expression diversity
3.59
Empathy
3.31
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
Chinese5 / 133.323.3 – 3.44.23.33.6—4,531