Overall Intelligence race
A weighted blend of every language-model race on the site. Drag the sliders to build your own definition of 'best'.
- Leader
- Fable 5.1
- Margin
- 1.0 pts
- 1.1% ahead
- Weeks at #1
- 1
- 5 total
- Changes
- 9
- in 2026
Warming up the track…
Re-weight this race
Drag to say what matters to you. The track re-sorts live and weeks-at-#1 are recomputed for your weighting.
Score history
Top 6 today over the leader's frontier · click to jump to a week
Reigns at #1
Longest: Gemini 3 Pro, 13 weeks (from Nov 2025).
Inside this race
What makes up overall intelligence
Why this race matters
No single benchmark captures usefulness. A transparent, adjustable blend is the closest thing to a fair overall ranking.
How it is scored
Weighted average of the model's percentile in each child race. A model needs results covering at least half of the weight to be ranked.
Data provenance
AIModelRace composite
Each child race is converted to a percentile within its field before weighting.
Composite race: each model's within-field percentile in every child race, weighted as shown. A model needs results covering at least half of the weight to be placed. How composites work