# ARC Prize reports Carbon used more reasoning tokens than Argon

> Original title: @Google On each of the ARC Prize benchmarks, Carbon used more reasoning tokens than Argon.

- Source: ARC Prize
- Published: 2026-11-10T20:31:53.000Z
- Bad Influence: https://badinfluence.news/items/vver8lsyzn2er2on8q65hohfi
- Original: https://x.com/arcprize/status/2120253129270640817

## Summary

ARC Prize says Carbon used more reasoning tokens than Argon on each of its benchmarks. On ARC-AGI-3 Public games, Carbon at high reasoning averaged 6k reasoning tokens for its first action, compared with 2k for Argon.

## Post

@Google On each of the ARC Prize benchmarks, Carbon used more reasoning tokens than Argon.

For example, on ARC-AGI-3 Public games, Carbon at high reasoning averaged 6k reasoning tokens for its first action vs 2k for Argon.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWym-6AWEAAKPv_.jpg&mode=thumb&exp=1794528000&sig=7ee398dfb220b559)