# ARC Prize reports Fable 5.2 scores 93.8% on ARC-AGI-2

> Original title: @AnthropicAI On ARC-AGI-2, Fable 5.2's 93.8% is the third-highest model score we've seen, after GPT-6 Astra's 95.0% and GPT-6.1 Sol's 94.2%.

- Source: ARC Prize
- Published: 2026-11-09T19:13:46.000Z
- Bad Influence: https://badinfluence.news/items/p1ydkpi427h4t3h2gddplmfa4
- Original: https://x.com/arcprize/status/2119871082756800545

## Summary

ARC Prize says Anthropic's Fable 5.2 scored 93.8% on ARC-AGI-2, the third-highest model score it has recorded. GPT-6 Astra scored 95.0% and GPT-6.1 Sol scored 94.2%, ranking ahead of Fable 5.2.

## Post

@AnthropicAI On ARC-AGI-2, Fable 5.2's 93.8% is the third-highest model score we've seen, after GPT-6 Astra's 95.0% and GPT-6.1 Sol's 94.2%.

Full results: https://arcprize.org/results/anthropic-claude-fable-5-2

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWtLg2uW8AAWX9J.jpg&mode=thumb&exp=1794528000&sig=25f438a5fb344fbf)