Revision History
Muse Code · 6 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: cite the Muse Spark model page for the benchmark comparison; date the Python SDK to 1.3.1 (21 Sep); scope the missing-tools issue to Windows; add the voice-input difference
Version 6 · Oct 1, 2026, 09:37 AM
- Correction: updated platforms (Windows native from 16 Sep 2026, not macOS/Linux only), subscription allowances (High 3x->5x, Power 10x->20x), Contributor rate limits (60 rpm/2.1M tpm -> 100 rpm/3M tpm), and the Workflows availability rule (not Linux-only; needs the workflow script engine, absent from the Apple silicon build). Added Monitor (29 Sep), Windows support, release 1.4.x changelog, /loop scheduling, Meta Model API general availability and the 1 Oct Terminal-Bench 2.1 leaderboard.
Version 5 · Oct 1, 2026, 08:53 AM
- Added a Muse Spark 1.3 section: availability in Muse Code from September 2, 2026, max reasoning from September 4, Meta's efficiency claims and coding benchmarks with attribution, and unchanged pricing; updated the model field and the post-beta product-page note.
Version 4 · Sep 5, 2026, 03:14 PM
- Updated the post-beta release, local session messaging, Workflows, rewind, SDK preview, and subscription pricing
Version 3 · Sep 2, 2026, 04:44 AM
- Correction: Muse Spark 1.2 does not beat GPT-5.6 Terra on every coding chart (Terra leads DeepSWE 1.1, 64.8% vs 59.3%, per Meta's own chart); Terminal-Bench 2.1 submissions run through the harbor framework, not a benchmark-owned harness.
Version 2 · Aug 7, 2026, 05:40 PM