Skip to content
AIMODELRACE
The main eventPhoto finish

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
Opus 5.5
Margin
0.3 pts
0.3% ahead
Weeks at #1
5
in a row
Changes
11
in 2026

Warming up the track…

Oct 20, 2026Opus 5.5 leads
2025Apr ’25Jul ’25Oct ’252026Apr ’26Jul ’26Oct ’26

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.

14%
14%
9%
9%
10%
9%
13%
7%
8%
6%

Score history

Top 6 today over the leader's frontier · click to jump to a week

#1 frontierOpus 5.5Fable 5.1Gemini 4 Argon3.8 FlashGPT-6.1 SolSpark 1.3
20.040.060.080.0100.02025Apr ’25Jul ’25Oct ’252026Apr ’26Jul ’26Oct ’26

Reigns at #1

Longest: GPT-5, 15 weeks (from Aug 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.

Unit: indexHigher is betterPhoto finish under 0.6 ptsDominant over 3.5 pts

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