Meta Launches Muse Code Beta and Muse Spark 1.2 Coding Model
On August 5, 2026, Meta released Muse Code (beta), a terminal coding agent with persistent background subagents and a replay-exact event log, powered by Muse Spark 1.2—a coding-focused update to Muse Spark 1.1 available in the agent and Meta Model API with expanded global access.
TLDR
Meta on August 5, 2026 shipped Muse Code (beta)—a terminal coding agent—powered by Muse Spark 1.2, the newest Muse Spark tier. Install path: curl -fsSL https://dev.meta.ai/install.sh | bash (macOS/Linux). Muse Spark 1.2 is available in Muse Code and Meta Model API with expanded global access. The stack targets long-horizon multi-file / whole-repo engineering against Claude Code, Codex, and other agent harnesses.
What shipped
| Piece | Detail (Meta primary) |
|---|---|
| Muse Code | Terminal agent: plan, implement, validate multi-file changes across large repos |
| Background agents | Persistent specialized subagents across a session (not one-shot spawns) |
| Runtime | Local event log of model calls, tools, approvals, edits — replay-exact, restart-safe |
| Bundled skills | /plan (approval-gated plan), /grill (stress-test plan), /goal (objective completion) |
| Muse Spark 1.2 | Coding-focused update to 1.1: more coding train compute, environment diversity; co-trained with Muse Code harness |
| Long-horizon | Whole-repo generation, large projects, auto-research; planning + goal conditioning + context compaction |
| Case study | GPU kernel optimization over 1,000+ tool calls (up to 24 hours) on Hopper KDA/MLA kernels |
Meta frames 1.2 as an interim step “toward the frontier, with larger and much more capable models on the way.”
Ranking context
Lab-reported: Meta publishes Terminal-Bench 2.1, DeepSWE 1.1, and internal coding-bench charts on the launch post (see methodology report linked from the blog). Kernel case studies claim progressive speedups vs. baseline Triton/PyTorch references under tool-call budgets.
Independent (as available near launch):
- LMArena / Arena: public leaderboard snapshots list muse-spark-1.2 (xHigh) with Elo-style scores (e.g. ~1290±18 on a Hugging Face Arena snapshot around launch week)—treat as live board, not a frozen vendor claim.
- Artificial Analysis: original Muse Spark placed in the high tier of the Intelligence Index at base launch (mid-50s historically; base Muse Spark often cited ~52 near first GA). 1.2-specific full Index breakdowns were still landing around launch day—prefer Meta coding benches + any same-day AA posts over inventing a 1.2 Index number.
- Coding vs. general chat: prior AA coding-index snapshots had base Muse Spark lagging GPT‑5.4 / Gemini 3.1 Pro / top Claude coding configs—1.2 is Meta’s explicit answer to that gap.
If Arena votes for 1.2 are thin in the first days, say so rather than overclaiming rank.
Product-line de-dupe
Distinct from Muse Image, Muse Spark 1.1 (July 9), and Llama open weights. This is the coding agent + Spark 1.2 model product line. Same-day Meta cyber-eval breach disclosure (Muse Spark via Irregular) is a separate safety story—not folded into the launch post.
Why this story matters
Meta is no longer only shipping chat/multimodal Muse—it is competing in the terminal agent market where Anthropic (Claude Code), OpenAI (Codex / ChatGPT Work), and Cursor-class tools already live. Co-training model + harness is the real product thesis: Spark 1.2 without Muse Code is incomplete. Watch API pricing/rate limits, independent coding arena movement, and whether “larger models on the way” lands before year-end.