Meta model product
Muse Spark 1.2
2 is a proprietary multimodal reasoning model from Meta Superintelligence Labs for long-horizon coding and whole-repository agentic work.
Updated Oct 23, 2026. Default version: Muse Spark 1.2
LLMBoard Score76.2Muse Spark 1.2
Coverage80%2 benchmark families
Context window1MTokens
Official input price$1.25Meta API
Muse Spark 1.2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Muse Spark 1.2 Benchmark Results
Benchmark scores for Muse Spark 1.2.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMeta Internal Coding Bench | Score70.60% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLiveBench reasoning (2026-06-25) | Score90.00 score | Rank07 | Participants43 | Percentile85.71% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Vision Style Control | Score1,292.67 rating | Rank08 | Participants113 | Percentile93.75% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,492.04 rating | Rank09 | Participants218 | Percentile96.31% | EvidenceA | Evaluated |
| BenchmarkAA SciCode Subtasks | Score57.41% | Rank10 | Participants89 | Percentile89.77% | EvidenceB | EvaluatedN/A |
| BenchmarkLiveBench instruction (2026-06-25) | Score74.33 score | Rank10 | Participants43 | Percentile78.57% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score5.79% | Rank11 | Participants44 | Percentile76.74% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,482.36 rating | Rank13 | Participants218 | Percentile94.47% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,479.32 rating | Rank13 | Participants131 | Percentile90.77% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,304.22 rating | Rank14 | Participants113 | Percentile88.39% | EvidenceA | Evaluated |
| BenchmarkAA HLE Text No Tools | Score45.46% | Rank14 | Participants200 | Percentile93.47% | EvidenceB | EvaluatedN/A |
| BenchmarkLiveBench math (2026-06-25) | Score91.20 score | Rank16 | Participants43 | Percentile64.29% | EvidenceB | EvaluatedN/A |
| BenchmarkTerminal-Bench 2.1 | Score82.90% | Rank19 | Participants48 | Percentile61.70% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score17.71% | Rank19 | Participants200 | Percentile90.95% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Agent Tool Hallucination | Score0.18% | Rank24 | Participants44 | Percentile46.51% | EvidenceA | Evaluated |
| BenchmarkAA Omniscience Accuracy | Score45.38% | Rank28 | Participants201 | Percentile86.50% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score-8.58% | Rank31 | Participants44 | Percentile30.23% | EvidenceA | Evaluated |
| BenchmarkAA GPQA Diamond | Score90.40% | Rank33 | Participants199 | Percentile83.84% | EvidenceB | EvaluatedN/A |
| BenchmarkDeepSWE 1.1 | Score59.30% | Rank34 | Participants51 | Percentile34.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score-8.59% | Rank34 | Participants44 | Percentile23.26% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,533.84 rating | Rank35 | Participants107 | Percentile67.92% | EvidenceA | Evaluated |
| BenchmarkAA LCR v1.1 | Score79.00% | Rank35 | Participants193 | Percentile82.29% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Agent Praise Complaint | Score-11.39% | Rank36 | Participants44 | Percentile18.60% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Bash Reliability | Score-3.99% | Rank36 | Participants44 | Percentile18.60% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score-6.75% | Rank37 | Participants44 | Percentile16.28% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Bash Reliability No Prereq | Score-3.98% | Rank38 | Participants45 | Percentile15.91% | EvidenceA | Evaluated |
Muse Spark 1.2 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categoryindustry legal and government | Rank02 | Rating / score1,526.66 | Votes757 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank03 | Rating / score1,502.36 | Votes1,717 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank04 | Rating / score1,517.46 | Votes757 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank05 | Rating / score1,513.76 | Votes660 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank05 | Rating / score1,514.07 | Votes1,393 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank06 | Rating / score1,502.18 | Votes1,393 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank06 | Rating / score1,514.32 | Votes352 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank06 | Rating / score1,531.37 | Votes3,594 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank07 | Rating / score1,541.79 | Votes2,474 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank08 | Rating / score1,484.43 | Votes1,717 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank08 | Rating / score1,306.63 | Votes1,343 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank08 | Rating / score1,292.67 | Votes1,948 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank09 | Rating / score1,495.95 | Votes660 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank09 | Rating / score1,461.96 | Votes196 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank09 | Rating / score1,508.21 | Votes7,067 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank09 | Rating / score1,485.62 | Votes5,780 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank09 | Rating / score1,492.04 | Votes9,578 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank09 | Rating / score1,489.42 | Votes308 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank10 | Rating / score1,488.62 | Votes3,794 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank10 | Rating / score1,469.98 | Votes196 | ObservationsN/A | Result date |
| Arenaagent bash recovery steps | Categoryoverall | Rank11 | Rating / score0.06 | VotesN/A | Observations58.1K | Result date |
| Arenatext | Categoryindustry software and it services | Rank11 | Rating / score1,505.28 | Votes3,594 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank11 | Rating / score1,487.78 | Votes1,617 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank12 | Rating / score1,475.94 | Votes5,780 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank12 | Rating / score1,483.56 | Votes308 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexclude ties | Rank12 | Rating / score1,489.80 | Votes7,067 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank12 | Rating / score1,518.60 | Votes3,594 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank12 | Rating / score1,490.61 | Votes1,308 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank12 | Rating / score1,312.75 | Votes1,343 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank13 | Rating / score1,491.51 | Votes7,067 | ObservationsN/A | Result date |
Muse Spark 1.2 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.25 input, $4.25 output per 1M
- Official provider
- Meta
- Lowest third-party
- From $1.25 input, $4.25 output per 1M via OrcaRouter
- Tracked offerings
- 18
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOrcaRouter | Provider model IDmeta/muse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDmeta/muse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderMeta | Provider model IDmuse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDmeta/muse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDmeta/muse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDmeta/muse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderOpenCode | Provider model IDmuse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderEmpirioLabs AI | Provider model IDmuse-spark-1-2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDmeta/muse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDmuse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDmeta/muse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderAbacus | Provider model IDmuse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderOpper | Provider model IDmuse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDmeta/muse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderCommandCode | Provider model IDmeta/muse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderEden AI | Provider model IDmeta/muse-spark-1.2 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderAI/ML API | Provider model IDmeta/muse-spark-1.2 | Regionglobal | Input / 1M$1.32 | Output / 1M$4.5 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDmuse-spark-1.2 | Regionglobal | Input / 1M$1.38 | Output / 1M$4.68 | Context1M | Updated |
Muse Spark 1.2 Runtime Performance
Provider-specific output speed and catalog latency for Muse Spark 1.2. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Muse Spark 1.2 Specifications
Technical details for the model's default version.
- Version
- Muse Spark 1.2
- Released
- Aug 5, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 1M
- Max output
- 131.1K
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Muse Spark 1.2 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionMuse Spark 1.2 | Released | LLMBoard76.20 | ParametersN/A | Context1M | Max output131.1K | Open weightsNo | LicenseProprietary |
Models similar to Muse Spark 1.2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ME
Muse Spark Open
Meta
ME
Muse Wonder
Meta
ME
Muse Spark
Meta
ME
Muse Spark 1.1
Meta
ME
Muse Wonder Full
Meta
ME
Muse Spark 1.3
Meta
What is Muse Spark 1.2?
Key information about Muse Spark 1.2 and its available data.
2 is Meta Superintelligence Labs' proprietary multimodal reasoning model, with a 1,048,576-token context window for long-horizon coding and whole-repository agentic work. It is available through the Meta Model API in standard and contributor tiers.
Data as of 2026-10-22.
FAQ
Common questions about Muse Spark 1.2.
When was Muse Spark 1.2 released?
Muse Spark 1.2's default version was released on Aug 5, 2026.
How much does Muse Spark 1.2 cost?
Muse Spark 1.2's official API price is $1.25 per million input tokens and $4.25 per million output tokens via Meta. The lowest tracked third-party offer starts at $1.25 input and $4.25 output via OrcaRouter.
Who created Muse Spark 1.2?
Muse Spark 1.2 was created by Meta.
What is the context window for Muse Spark 1.2?
The default version has a 1M token context window.
Is Muse Spark 1.2 open weight?
No. The default version is not marked as having publicly available weights.