Muse Spark 1.1
- In Input modalities: TextImageAudioVideoPDF Out Output modalities: Text
- Reasoning· minimal, low, medium, high, xhigh
- Tool use
- Structured output
Prices
1 offering · prices as listedmuse-spark-1.1| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | $1.25 | $0.15 | $4.25 |
Prices from Meta Model API pricing and rate limits (opens in a new tab) (checked Nov 8, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Open weights
- —
- Family
- muse-spark
- Model ID
Not stated on Meta’s pages: max input, reasoning can be off, max thinking budget, built-in tools, knowledge cutoff, aliases.
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 154.9
#44 of 118 listed models · CI 152.3–157.6
- LMArena Text 1,491
#12 of 163 listed models · CI 1,487–1,495 · 45,555 votes
- Epoch AI · Chess Puzzles 34%
#45 of 85 listed models · xhigh effort · ±4.76
- Epoch AI · SimpleQA Verified 57.8%
#18 of 84 listed models · ±1.57
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Nov 4 – 5, 2026
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Nov 8, 2026
- EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · License · as of Oct 24 – 28, 2026
- LiveBench (White et al.), release 2026-06-25, livebench.ai, licensed CC BY-SA 4.0. This board, adapted from it, is shared under CC BY-SA 4.0. · License · as of Jun 25, 2026
- changes we made
Provider-reported scores
Published by Meta, under the conditions it states| Benchmark | Setting | Score |
|---|---|---|
| Humanity's Last Exam | with tools (bash and browser, blocklist), full 2,500 questions, xhigh reasoning effort | 62.1% |
| no tools, xhigh reasoning effort | 52.2% | |
| OSWorld-Verified | 361-task split excluding Google Drive tasks, GUI tool only, max 200 steps, xhigh reasoning effort | 80.8% |
| DeepSearchQA | F1, browser tools, xhigh reasoning effort | 84.9% |
| Terminal-Bench 2.1 | bash-tool-only harness, 89 tasks, pass@1 averaged over 5 attempts, xhigh reasoning effort | 80% |
| DeepSWE 1.1 | fork of mini-swe-agent, internet disabled, pass@1 averaged over 5 attempts, xhigh reasoning effort | 53.3% |
| MRCR v2 | 8-needle, 512K–1M tokens (1M context), xhigh reasoning effort | 54.1% |
| CharXiv Reasoning | with code-execution tool, 1,000 validation questions, xhigh reasoning effort | 88.4% |
Changes
All changes →No changes recorded yet.
Sources
- Muse Spark 1.1 Evaluation Report (PDF, Meta) (opens in a new tab) research.meta.ai · checked Sep 26, 2026
- Meta Model API models (opens in a new tab) dev.meta.ai · checked Nov 8, 2026
- Meta Model API: reasoning (opens in a new tab) dev.meta.ai · checked Nov 8, 2026
- Meta Model API pricing and rate limits (opens in a new tab) dev.meta.ai · checked Nov 8, 2026
- Introducing Muse Spark 1.1 and the Meta Model API (opens in a new tab) ai.meta.com · checked Nov 8, 2026
- models.dev: muse-spark-1.1 (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
Meta’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Meta · United States · ai.meta.com
Related models
Snapshots, the same family and other models from this provider