# Artificial Analysis ranks Fable 5.2 first on its Intelligence Index at 65

> Artificial Analysis scores Fable 5.2 at 65 on its Intelligence Index v5, ahead of Gemini 4 Carbon at 60 and Opus 5.5 at 59.

- Status: reported (One outlet, not independently verified yet.)
- Topic: Models
- Published: 2026-11-10T06:35:42+00:00
- Updated: 2026-11-10T09:09:49.233819+00:00
- Web page: https://ai-news.ikangai.com/story/artificial-analysis-ranks-fable-5-2-first-on-its-intelligence-index-at-65/
- Seen in: Latent Space
- Change: research (Research)

Artificial Analysis ranks Claude Fable 5.2 first on its Intelligence Index v5, with a score of 65 at max effort. That puts it five points ahead of Gemini 4 Carbon at high effort (60) and six ahead of Anthropic's Opus 5.5 at max (59). GPT-6 Astra at max scored 57, and Fable 5.1 at max scored 49.

Fable 5.2 offers five effort levels: low, medium, high, xhigh and max. Artificial Analysis lists its top score at max. The same post says Fable 5.2 scores 62 at high and xhigh while using about 98k output tokens per task, against 173k for Opus 5.5 at max. At max, cost per task is about $26.5, roughly 2.6 times Opus 5.5 at max ($10.0) and about twice Fable 5.1 at max ($12.99). Fable 5.2 is priced at $8 per million input tokens and $40 per million output tokens, 20% below Fable 5.1's $10 and $50. The higher bill therefore comes from the number of tokens the model generates, not from its rate card.

The same evaluations include new records. Fable 5.2 scored 80% on HLE-Diamond, against a previous best of 69%, and 67 on AA-Omniscience v1.1, against a previous best of 54. It reached 73% on Terminal-Bench-Science, up from 65%, and 77% on CritPt v2 hard, up from 72%.

Other results are closer. On AA-Briefcase, Fable 5.2 scored 1785 Elo, which Artificial Analysis describes as within the confidence interval of Opus 5.5 at 1800 and behind Sonnet 5.5 at 1813. On Terminal-Bench 4.0 it scored 60%, level with Opus 5.5 and behind Kimi K3.1 Pro (67%), Gemini 4 Carbon (65%) and Sonnet 5.5 (64%). On AutomationBench-AA it scored 76%, ahead of Opus 5.5 at 70% but behind Gemini 4 Carbon at 78%.

Effort setting also matters on other evaluations. On the Vals Index, high was the best-performing setting, above xhigh and max.

## Why it matters

Independent index results help buyers compare frontier models, but the lead depends on effort setting and benchmark mix, so results need checking against their own workloads.

---

AI wrote this summary from the sources listed, and nobody reviewed it individually before publication. Check the original source before you rely on it.

Cite as: IKANGAI AI News, "Artificial Analysis ranks Fable 5.2 first on its Intelligence Index at 65", 2026-11-10, https://ai-news.ikangai.com/story/artificial-analysis-ranks-fable-5-2-first-on-its-intelligence-index-at-65/
