Overall Intelligence race
A weighted blend of every language-model category on the site. Drag the sliders to build your own definition of 'best'.
- Leader
- Opus 5.5
- Margin
- 0.1 pts
- 0.1% ahead
- Weeks at #1
- 4
- in a row
- Changes
- 6
- 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: 2.5 Pro, 15 weeks (from Mar 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
Normalised child-category scores, weighted and averaged. Weights are user-adjustable.
Data provenance
Independent measurement of intelligence indices, speed, latency and price.
Crowd-sourced blind pairwise votes, reported as Elo-style ratings.
AIModelRace composite
Each child race is normalised to 0-100 before weighting.
Scores here are illustrative placeholders that mimic real benchmark patterns. Swap in live data through the score provider. Methodology