Overall score
74.92
95% CI [73.79, 76.00]
Based on 285 sessions
Rank 10 of 12 models on the Overall leaderboard
Three goals
● Worlds 50%66.46
● Stories 25%70.81
● Preferences 25%95.97
Six dimensions
4456100589796
BasicsLogicKnowledgeDiversityContent LogicInteraction
Scores by language
Tested November 1, 2026| Language | Rank | Overall | 95% CI | Worlds | Stories | Preferences | Sessions |
|---|---|---|---|---|---|---|---|
| Overall | 10 / 12 | 74.92 | 73.8 – 76.0 | 66.5 | 70.8 | 96.0 | 285 |
| Chinese | 11 / 12 | 69.33 | 68.1 – 70.7 | 58.2 | 67.0 | 94.0 | 150 |
| English | 9 / 12 | 81.14 | 80.0 – 82.2 | 75.7 | 75.1 | 98.1 | 135 |