Muse Sparkvso1-preview
Muse Spark | o1-preview | |
|---|---|---|
| Specifications | ||
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $15.00 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $60.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $7.50 |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 89.5% | 73.3% |
| BenchmarksPublished by one model only | ||
Gray Swan IPI · k = 1Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | 2.9% | — |
Gray Swan IPI · k = 10Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | 14.3% | — |
Gray Swan IPI · k = 15Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | 16.5% | — |
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. | 55% | — |
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. | 77.4% | — |
DeepSWE 1.1Agentic 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. (Version 1.1 of the test.) Higher is better. | 10% | — |
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. | 67.3% | — |
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. | 82.2% | — |
JobBenchProfessional tool use — Tests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | 17% | — |
Toolathlon-VerifiedPersonal tool use — Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | 49.4% | — |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 50.4% | — |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 42.5% | — |
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. | 53.3% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 88.9% | — |
BabyVisionVisual reasoning — Tests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better. | 39.9% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 80.4% | — |
| Overview | ||
| Company | Meta | OpenAI |
| Release date | Apr 8 2026 | Sep 12 2024 |
| Access | Proprietary | Proprietary |
Other comparisons
Muse SparkvsClaude Opus 5o1-previewvsClaude Opus 5Muse SparkvsGemini 3.7 Flasho1-previewvsGemini 3.7 FlashMuse SparkvsGrok 4.6o1-previewvsGrok 4.6Muse SparkvsDeepSeek-V4-Pro-0813o1-previewvsDeepSeek-V4-Pro-0813Muse SparkvsMistral Medium 3.5o1-previewvsMistral Medium 3.5Muse SparkvsKimi K3o1-previewvsKimi K3
Frequently asked questions
Muse Spark leads o1-preview on 1 of the 1 benchmark they both report (GPQA Diamond). Only o1-preview has a verified first-party API price: $15.00 per million input tokens and $60.00 per million output tokens. No pay-as-you-go API rate is tracked for Muse Spark. o1-preview shipped 573 days before Muse Spark, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On GPQA Diamond, Muse Spark leads at 89.5% vs o1-preview at 73.3%.
Muse Spark was released by Meta on Apr 8 2026.
o1-preview was released by OpenAI on Sep 12 2024.
Muse Spark leads on GPQA Diamond — Muse Spark 89.5% vs o1-preview 73.3%.
Only o1-preview has a verified first-party API price: $15.00 per million input tokens and $60.00 per million output tokens. No pay-as-you-go API rate is tracked for Muse Spark. Rates are pay-as-you-go API prices verified on August 18, 2026.