Meta
Meta's proprietary coding-focused multimodal reasoning model for long-horizon agents, complex debugging, codebase understanding, tool and computer use, and audio-visual workflows through Meta Model API.
30.3
Quality Score
1292
Arena ELO
Undisclosed
Parameters
1M
Context
This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.
16 of 22 public signals
Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.
This model has official provider benchmark evidence, but not a normalized independent benchmark table yet.
A full normalized benchmark row is not available for this model yet.
Official benchmark evidence is already available below, so this release is still being tracked while the normalized table catches up.
Sign in to join the discussion
0
Downloads
0
Likes
Aug 2026
Released
4/5 signals
3/4 signals
4/5 signals
1/4 signals
4/4 signals
Parameters
—
Training compute
Not reported
Dataset scale
Not reported
Base model
Not reported
Source-reported access: API access · Confident confidence
Gaps we are still tracking
These are recent benchmark or leaderboard claims from official provider sources. They are useful for freshness and context, but they are not treated the same as normalized independent benchmark rows.
To understand whether we're making genuine progress on reasoning, we entered our AI models in five STEM Olympiad competitions. The results: 🏅 Asian Physics Olympiad (APhO): Perfect score, theory exam
To understand whether we're making genuine progress on reasoning, we entered our AI models in five STEM Olympiad competitions. The results: 🏅 Asian Physics Olympiad (APhO): Perfect score, theory exam 🏅 International Physics Olympiad (IPhO): Perfect score, theory exam 🥇 https://t.co/fh1h8I1d3S
View sourceIntroducing Muse Code and Muse Spark 1.2
Skip to main content AI Research AI Developers Try Meta AI Introducing Muse Code and Muse Spark 1.2 August 5, 2026 · 4 minute read We're excited to release Muse Code (beta), a terminal coding agent powered by Muse Spark 1.2, our newest model. It can coordinate multiple persistent subagents for each task, solving difficult problems faster, more accurately, and with less intervention. Muse Code Async Background Agents Muse Code operates with a simple agent loop plus a set
View sourceIntroducing Muse Code and Muse Spark 1.2
Introducing Muse Code and Muse Spark 1.2 | Meta AI Research Skip to main content AI Research AI Developers Try Meta AI Introducing Muse Code and Muse Spark 1.2 August 5, 2026 · 4 minute read We're excited to release Muse Code (beta), a terminal coding agent powered by Muse Spark 1.2, our newest model. It can coordinate multiple persistent subagents for each task, solving difficult problems faster, more accurately, and with less intervention. Muse Code Async Background Ag
View source1292
ELO Score
1277 - 1307
95% Confidence
+/-15 points
1.8K
Battles
Sep 5, 2026
Last Updated