As of: 2026-10-13 07:38 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code). Human editor: Adam Bicz.
Canonical page: https://postcutoff.com/p/x-artificialanlys-2109697086543581411/

# Artificial Analysis thread (reply 1): Muse Wonder Full top three on six of ten Intelligence Index evaluations

Artificial Analysis (@ArtificialAnlys), X, 2026-10-12.
Source: https://x.com/ArtificialAnlys/status/2109697086543581411

## Why it matters

Independent per-benchmark results for Muse Wonder Full from Artificial Analysis' launch-day thread.

## Summary

Posted Oct 12, 2026 (17:25 UTC). First reply in Artificial Analysis' own thread (root: x-ArtificialAnlys-2109697083519447118). Muse Wonder Full (max) 'places in the top three on six of the ten' Intelligence Index v4.3 evaluations: first on CritPt (33%) and GDP.pdf (33%), second on GDPval-AA v2.1 (1857 Elo), third on AA-Briefcase (1729 Elo), AutomationBench-AA (71%) and SciCode (63%). The leads on CritPt and GDP.pdf are 'narrow, with the nearest competitors scoring 31-32%', and the GDPval-AA result is within the confidence intervals of Claude Opus 5.5 (1866) and Claude Sonnet 5.5 (1838). Terminal-Bench 4.0 rose from 33% (Muse Spark 1.3) to 57%, 'level with Gemini 4 Argon (high)'.

_Metrics as of 2026-10-13 via api.fxtwitter.com: 16,210 views, 98 likes, 7 reposts._

## Archived text

> Muse Wonder Full (max) places in the top three on six of the ten Artificial Analysis Intelligence Index v4.3 evaluations:
> 
> ➤ #1 on CritPt (33%) and GDP.pdf (33%)
> 
> ➤ #2 on GDPval-AA v2.1 (1857 Elo)
> 
> ➤ #3 on AA-Briefcase (1729 Elo), AutomationBench-AA (71%) and SciCode (63%)
> 
> The leads on CritPt and GDP.pdf are narrow, with the nearest competitors scoring 31-32%. On GDPval-AA v2.1, its result is within the confidence intervals of Claude Opus 5.5 (max w/ fallback, 1866) and Claude Sonnet 5.5 (max w/ fallback, 1838)
> 
> Its largest improvement over Muse Spark 1.3 is Terminal-Bench 4.0: 33% to 57%, bringing it level with Gemini 4 Argon (high)

Archived 2026-10-13 via fxtwitter (unofficial).
Counts: 16,333 views, 98 likes, 7 reposts, 3 replies (at fetch time)
Media: https://pbs.twimg.com/media/HUclBbraQAA9BPk.jpg?name=orig

## Cited in

- 2026-10-12: [Meta releases Muse Wonder and Muse Wonder Full, its first frontier-class models](https://postcutoff.com/e/2026-10-12-meta-muse-wonder/)