# Mike Knoop says the science of AI evals is still nascent

> Original title: The science of evals is quite nascent given how important they are

- Source: Mike Knoop
- Published: 2026-10-28T17:05:40.000Z
- Bad Influence: https://badinfluence.news/items/a8lbreawtbw08tiqn97a21fsp
- Original: https://x.com/mikeknoop/status/2115490192719245436

## Summary

Mike Knoop says the science of evals is quite nascent given how important they are. The post cites ARC Prize data showing a power-curve fit of ARC-AGI-2 scores from ARC-AGI-1 scores (v2 = v1^4.53) explaining about 98% of the variation. Models tied on ARC-AGI-1 can still differ by over 20 percentage points on ARC-AGI-2.

## Post

The science of evals is quite nascent given how important they are

## Quoted post @arcprize

> Plotting ARC-AGI model scores reveals a strong relationship across all three benchmarks.
> 
> For example, the power curve v2 = v1^4.53 explains about 98% of the variation in ARC-AGI-2 scores. Models tied on ARC-AGI-1 can still differ by over 20 percentage points on ARC-AGI-2.

https://x.com/arcprize/status/2115475078175395986