Open vs Proprietary Intelligence
AA Index v4.1 595 models Updated 14 Aug 2026
Artificial Analysis Intelligence Index

Open weights are only 2.4 months behind the proprietary frontier.

Every point is a model release. The frontier lines track the running best score in each camp, and the lag is the horizontal distance between them — how long open weights needed to reach a level proprietary models had already shipped.

Smoothing
595 models scored
Current lag
2.4 months
Smoothed, 12-month window
Best open weights
59.7
Kimi K3 (max)
16 Jul 2026
Best proprietary
63.1
Claude Opus 5 (Adaptive Reasoning, Max Effort)
24 Jul 2026
Index gap
3.4
Matched by Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
09 Jun 2026

The two frontiers

The stepped lines are the real frontier — each step is a model that set a new record. The soft curve behind is the smoothed trend, and the shaded band is the standing gap. Faint dots are all other releases.

Open weights Proprietary Actual frontier Smoothed trend

Lag over time

How many months open weights trailed proprietary at each point in history. A wider smoothing window fits the trend across more releases, so the line follows the underlying pace instead of the accident of release timing.

Smoothed trend Raw step lag

Lag by capability level

The same gap read along the capability axis instead of the calendar: to reach a given index score, how much longer did open weights need than proprietary did? Rising to the right means the gap widens as models get stronger; falling means open weights are closing in at the frontier.

Smoothed trend Actual release dates

Where the data came from

Two independent acquisition tracks are merged field by field, with the more certain source winning each field rather than one source winning outright.

TrackStatusRecordsContributes
Website crawl live 51 Open-source licence category, reasoning flag
Artificial Analysis API live 608 Intelligence Index, release dates, coverage

Open-weights classification resolved from the website for 81 models, and inferred for 514 where neither source carried a flag.