Muse GlimmervsComposer 2.5
Muse Glimmer | Composer 2.5 | |
|---|---|---|
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | 30B | — |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.30DeepInfra | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $1.10Phala | — |
| Benchmarks | ||
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 51.2% | 54% |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 51.7% | 73% |
| BenchmarksPublished by one model only | ||
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 76% | — |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 79.8% |
DeepSWE 1.0Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. Higher is better. | — | 18% |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 81% |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 69.3% |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | 75.5% | — |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 22% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 83.5% | — |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 65.9% | — |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 953 | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 78.8% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 74% | — |
threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. | — | 1137 |
| Overview | ||
| Company | Meta | SpaceXAI |
| Release date | Aug 10 2026 | May 18 2026 |
| Access | Open Weight | Proprietary |
Other comparisons
Muse GlimmervsClaude Fable 5.1Composer 2.5vsClaude Fable 5.1Muse GlimmervsGPT-6 AstraComposer 2.5vsGPT-6 AstraMuse GlimmervsGemini 3.8 FlashComposer 2.5vsGemini 3.8 FlashMuse GlimmervsDeepSeek-V4.1-FlashComposer 2.5vsDeepSeek-V4.1-FlashMuse GlimmervsMistral Medium 3.5Composer 2.5vsMistral Medium 3.5Muse GlimmervsKimi K3Composer 2.5vsKimi K3
Frequently asked questions
Composer 2.5 leads Muse Glimmer on 2 of the 2 benchmarks they both report (SWE-Bench Pro, Terminal-Bench 2.1). Composer 2.5 shipped 84 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.
Muse Glimmer is open weight, while Composer 2.5 is proprietary.
On SWE-Bench Pro, Composer 2.5 leads at 54% vs Muse Glimmer at 51.2%. On Terminal-Bench 2.1, Composer 2.5 leads at 73% vs Muse Glimmer at 51.7%.