Overall score
69.52
95% CI [68.93, 70.09]
Based on 285 sessions
Rank 12 of 12 models on the Overall leaderboard
Three goals
● Worlds 50%56.25
● Stories 25%74.68
● Preferences 25%90.90
Six dimensions
462499659491
BasicsLogicKnowledgeDiversityContent LogicInteraction
Scores by language
Tested November 2, 2026| Language | Rank | Overall | 95% CI | Worlds | Stories | Preferences | Sessions |
|---|---|---|---|---|---|---|---|
| Overall | 12 / 12 | 69.52 | 68.9 – 70.1 | 56.3 | 74.7 | 90.9 | 285 |
| Chinese | 12 / 12 | 68.46 | 67.7 – 69.3 | 55.7 | 73.5 | 89.0 | 150 |
| English | 12 / 12 | 70.69 | 69.8 – 71.5 | 56.9 | 76.0 | 93.1 | 135 |