Personal Superintelligence Index
Progress Over Time
Interactive timeline showing model performance evolution on Personal Superintelligence Index
State-of-the-art frontier
Open
Proprietary
Personal Superintelligence Index Leaderboard
5 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Meta | — | — | — | ||
| 1 | Meta | — | — | — | ||
| 3 | Meta | — | — | — | ||
| 3 | Meta | — | 1.0M | $4.00 / $20.00 | ||
| 5 | Muse EmberNew Meta | — | 1.0M | $0.10 / $0.50 |
Notice missing or incorrect data?
What is Personal Superintelligence Index?
Internal composite of Agents' Last Exam, AutomationBench-AA, FocusBench, JobBench, GDP.pdf, VBT, and DRACO.
Personal Superintelligence Index is a text benchmark evaluating models on knowledge and agents tasks. LLM Stats tracks 5 models on this benchmark, scored on a 0–1 scale. The current average is 0.5, with the leader at 0.6.
Compare leaders on the best AI for knowledge and best AI for agents leaderboards.
Current leaders
Muse Wonder Full from Meta currently leads the Personal Superintelligence Index leaderboard with a score of 0.591 across 5 evaluated AI models.
FAQ
Common questions about the Personal Superintelligence Index benchmark and leaderboard.