Muse Spark 1.2
Made by Meta, released 5 Aug 2026. Epoch AI lists its access as “API access”. Appears strongest at coding among the models listed here.
In short
What it does well
- Coding: Top tier (15th of 77 listed models)
- Knowledge: Strong (14th of 43 listed models)
Where it falls short
- Writing: Middle (44th of 77 listed models)
What we don't know yet
- Hard maths problems: Not enough data
- School-competition maths: Not enough data
- Graduate-level science questions: Not enough data
- Fixing real software bugs: Not enough data
- Difficult coding tasks: Not enough data
The four ratings
- Top tier
- Strong
- Middle
- Behind the leaders
- Not enough data
Ratings compare only the 77 models listed here, in quarters, best first. “Not enough data” means no result yet. It is never a low score.
- Writing
- MiddleHow often people preferred its answers to writing prompts. 1,437 on Arena's scale · Source for Muse Spark 1.2 writing score (lmarena)
- Coding
- Top tierHow often people preferred its answers to coding questions. 1,506 on Arena's scale · Source for Muse Spark 1.2 coding score (lmarena)
- Maths
- Not enough dataNo result yet for hard maths problems.
- Knowledge
- StrongHow many short factual questions it answered correctly. 60.3% · Source for Muse Spark 1.2 knowledge score (epoch)
Evidence completeness: Partial evidence, 8 of 13 tests have a result.
Where it is relatively stronger or weaker
This compares each kind of request with the model's own overall position among the 77 listed models, using Arena's votes. It is about performance on different languages, kinds of request and topics, not about political or social bias.
Relatively stronger
No category stands out as clearly stronger than its overall position.
Relatively weaker
- Expert-level prompts: 43rd of 77 on prompts that need expert knowledge, against 14th of 77 overall. Source for Expert-level prompts
- Chinese: 32nd of 76 on questions asked in Chinese, against 14th of 77 overall. Source for Chinese
- Long prompts: 31st of 77 on long, detailed prompts, against 14th of 77 overall. Source for Long prompts
Show every category we can see
| Category | Position | Arena score | Votes | Source |
|---|---|---|---|---|
| Expert-level prompts Kind of request | 43rd of 77 | 1,477 95% range 1,460 to 1,494 | 1,217 | Source for Expert-level prompts |
| Hard prompts Kind of request | 17th of 77 | 1,492 95% range 1,484 to 1,499 | 7,435 | Source for Hard prompts |
| Long prompts Kind of request | 31st of 77 | 1,474 95% range 1,465 to 1,483 | 5,113 | Source for Long prompts |
| Longer conversations Kind of request | 9th of 77 | 1,496 95% range 1,481 to 1,511 | 1,727 | Source for Longer conversations |
| Chinese Language | 32nd of 76 | 1,510 95% range 1,491 to 1,530 | 1,000 | Source for Chinese |
| English prompts Language | 14th of 77 | 1,484 95% range 1,475 to 1,493 | 4,605 | Source for English prompts |
| French Language | 11th of 72 | 1,500 95% range 1,469 to 1,530 | 425 | Source for French |
| Non-English prompts Language | 14th of 77 | 1,475 95% range 1,467 to 1,483 | 7,118 | Source for Non-English prompts |
| Russian Language | 19th of 77 | 1,481 95% range 1,465 to 1,497 | 1,535 | Source for Russian |
| Spanish Language | 8th of 70 | 1,491 95% range 1,461 to 1,520 | 383 | Source for Spanish |
| Entertainment, sport and media Topic | 30th of 77 | 1,442 95% range 1,430 to 1,454 | 2,995 | Source for Entertainment, sport and media |
| Law and government Topic | 7th of 76 | 1,509 95% range 1,489 to 1,529 | 914 | Source for Law and government |
| Medicine and health Topic | 12th of 75 | 1,494 95% range 1,472 to 1,515 | 811 | Source for Medicine and health |
| Science Topic | 15th of 77 | 1,499 95% range 1,485 to 1,513 | 1,861 | Source for Science |
| Software and IT Topic | 11th of 77 | 1,508 95% range 1,498 to 1,517 | 4,340 | Source for Software and IT |
Bias: what we can and can't see
Our sources do not measure political lean, stereotyping, flattery (agreeing with you too readily) or safety behaviour, so we cannot say how any model does on those. What we can show is above: where a model is relatively stronger or weaker across languages, kinds of request and topics. Also, people voting in Arena can favour answer style, such as length and formatting, and our numbers do not adjust for that. See what AI bias means and what these tests can tell you.
Best-supported use cases
- Homework and maths: not ranked, because there is not enough data for the main test.
Where an alternative might be more suitable
- Writing and creating content: rated Middle on writing votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Homework and maths: no result on hard maths problems, so we cannot say. See which models the evidence does support.
- Research and checking facts: rated Strong on short factual questions. Compare it with Gemini 4 Argon, the best-supported choice for this task.
What it is
- Maker
- Meta
- Release date (Epoch AI)
- 5 Aug 2026
- Access, as listed by Epoch AI
- API access
- Licence, as listed by Arena
- Proprietary
- Maker's country (Epoch AI)
- United States of America
- Last observation in our data
- 28 Oct 2026
- Data last changed
- 29 Oct 2026, 14:36 UTC
We have not verified an official product page for this model, so we do not link to one.
How you can use it
Proprietary. The model's files are not published, so it is generally available only through its maker or partners the maker chooses.
How you can reach it (an app, a website, a developer API or a third-party tool) and what that costs are not covered by our benchmark data. Where we could verify prices from the maker's own pages, they are shown under Price. Epoch AI lists access as “API access”. See models, apps and harnesses and how AI pricing works.
Price
Price not independently verified
We have not been able to check this maker's own pricing page, so we show nothing for it.
We never infer subscription prices from API prices. New to “tokens” and “per million”? See how AI pricing works.
Good to remember
- Benchmarks are samples of tasks. None proves performance in every situation.
- Arena scores come from people choosing between answers. That measures preference, not correctness.
- Ratings are relative to the 77 models listed here. A different set would change them.
- Sources test models at different settings. Each result shows the setting used, and we do not adjust it.
The evidence, for the curious
Show all 13 tests with settings and sources
| Test | Result | Rating | Setting used | Source identifier | Observed | Links |
|---|---|---|---|---|---|---|
| Arena text: overall preference Arena 'text' leaderboard (Bradley-Terry rating, no style control) |
1,483 Arena score 95% range 1,476 to 1,489, 11,724 votes |
Top tier | effort: xHigh, bradley-terry rating | Muse Spark 1.2 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Muse Spark 1.2 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,437 Arena score 95% range 1,424 to 1,450, 2,491 votes |
Middle | effort: xHigh, bradley-terry rating | Muse Spark 1.2 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Muse Spark 1.2 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,506 Arena score 95% range 1,495 to 1,517, 2,987 votes |
Top tier | effort: xHigh, bradley-terry rating | Muse Spark 1.2 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Muse Spark 1.2 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,485 Arena score 95% range 1,461 to 1,508, 615 votes |
Strong | effort: xHigh, bradley-terry rating | Muse Spark 1.2 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Muse Spark 1.2 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,465 Arena score 95% range 1,455 to 1,475, 4,092 votes |
Strong | effort: xHigh, bradley-terry rating | Muse Spark 1.2 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Muse Spark 1.2 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,484 Arena score 95% range 1,470 to 1,497, 2,063 votes |
Top tier | effort: xHigh, bradley-terry rating | Muse Spark 1.2 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Muse Spark 1.2 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,534 Arena score 95% range 1,520 to 1,547, 2,155 votes |
Middle | effort: xHigh, bradley-terry rating | Muse Spark 1.2 (xHigh) lmarena · webdev/latest |
28 Oct 2026 | Source for Muse Spark 1.2 Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) | Not enough data | |||||
| OTIS Mock AIME 2024-2025 | Not enough data | |||||
| GPQA Diamond | Not enough data | |||||
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
60.3% share of questions correct standard error ±1.6 points |
Strong | effort: xhigh, best score across scorers | muse-spark-1.2_xhigh epoch · simpleqa_verified.csv |
27 Aug 2026 | Source for Muse Spark 1.2 SimpleQA Verified score (epoch) · Run details for SimpleQA Verified |
| SWE-bench Verified (Epoch runs) | Not enough data | |||||
| FrontierCode (reported by Cognition) | Not enough data | |||||
Missing evidence
Not enough data for these tests:
- FrontierMath Tiers 1-3 (v2)
- OTIS Mock AIME 2024-2025
- GPQA Diamond
- SWE-bench Verified (Epoch runs)
- FrontierCode (reported by Cognition)
Missing results are not low scores and do not count against the model.
Where a source gives no public run log, we cannot show the run behind the score. See data sources.
Not sure this is the right one?
Tell us what you need help with and we'll narrow the options down.