Meta model product
Muse Spark 1.3
3 is Meta Superintelligence Labs' proprietary multimodal reasoning model for long-running agentic, multi-agent, and coding workflows.
Updated Oct 23, 2026. Default version: Muse Spark 1.3
LLMBoard Score89.0Muse Spark 1.3
Coverage80%10 benchmark families
Context window1MTokens
Official input price$1.25Meta API
Muse Spark 1.3 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Muse Spark 1.3 Benchmark Results
Benchmark scores for Muse Spark 1.3.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAgentic IF Index (Internal) | Score57.80% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkJob Bench | Score64.90% | Rank01 | Participants9 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score98.50% | Rank01 | Participants25 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle, 512K-1M) | Score98.10% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE Atlas - Codebase QnA | Score59.40% | Rank01 | Participants7 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGDPval-AA | Score1,754.00 points | Rank04 | Participants17 | Percentile81.25% | EvidenceC | Evaluated |
| BenchmarkAA SciCode Subtasks | Score59.72% | Rank04 | Participants89 | Percentile96.59% | EvidenceB | EvaluatedN/A |
| BenchmarkLiveBench math (2026-06-25) | Score95.95 score | Rank04 | Participants43 | Percentile92.86% | EvidenceB | EvaluatedN/A |
| BenchmarkLiveBench instruction (2026-06-25) | Score78.00 score | Rank04 | Participants43 | Percentile92.86% | EvidenceB | EvaluatedN/A |
| BenchmarkTerminal-Bench 2.1 | Score88.80% | Rank05 | Participants48 | Percentile91.49% | EvidenceC | Evaluated |
| BenchmarkDeepSearchQA | Score89.40% | Rank06 | Participants13 | Percentile58.33% | EvidenceC | Evaluated |
| BenchmarkAA GPQA Diamond | Score94.14% | Rank06 | Participants199 | Percentile97.47% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score48.70% | Rank06 | Participants200 | Percentile97.49% | EvidenceB | EvaluatedN/A |
| BenchmarkAutomationBench | Score49.40% | Rank07 | Participants27 | Percentile76.92% | EvidenceC | Evaluated |
| BenchmarkDeepSWE 1.1 | Score75.40% | Rank07 | Participants51 | Percentile88.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld 2.0 | Score66.90% | Rank07 | Participants17 | Percentile62.50% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,659.26 rating | Rank07 | Participants107 | Percentile94.34% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,494.75 rating | Rank08 | Participants218 | Percentile96.77% | EvidenceA | Evaluated |
| BenchmarkAA CritPt | Score26.00% | Rank08 | Participants200 | Percentile96.48% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text | Score1,490.46 rating | Rank09 | Participants218 | Percentile96.31% | EvidenceA | Evaluated |
| BenchmarkLiveBench reasoning (2026-06-25) | Score89.65 score | Rank09 | Participants43 | Percentile80.95% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Agent Leaderboard | Score3.45% | Rank10 | Participants44 | Percentile79.07% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score6.08% | Rank10 | Participants44 | Percentile79.07% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score5.30% | Rank10 | Participants44 | Percentile79.07% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Tool Hallucination | Score0.61% | Rank10 | Participants44 | Percentile79.07% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,308.41 rating | Rank10 | Participants113 | Percentile91.96% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,289.59 rating | Rank10 | Participants113 | Percentile91.96% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score5.02% | Rank11 | Participants44 | Percentile76.74% | EvidenceA | Evaluated |
| BenchmarkLM Arena Document | Score1,470.66 rating | Rank12 | Participants38 | Percentile70.27% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,479.34 rating | Rank12 | Participants131 | Percentile91.54% | EvidenceA | Evaluated |
Muse Spark 1.3 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 | Categoryfrench | Rank02 | Rating / score1,520.44 | Votes638 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank02 | Rating / score1,514.84 | Votes275 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank03 | Rating / score1,512.58 | Votes275 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank03 | Rating / score1,490.06 | Votes344 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank03 | Rating / score1,366.49 | Votes257 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank04 | Rating / score1,511.29 | Votes638 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank04 | Rating / score1,487.83 | Votes344 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank05 | Rating / score1,501.01 | Votes3,484 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank05 | Rating / score1,384.43 | Votes257 | ObservationsN/A | Result date |
| Arenawebdev | Categoryimage to webdev | Rank05 | Rating / score1,640.39 | Votes5,679 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank05 | Rating / score1,652.73 | Votes1,275 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank06 | Rating / score1,501.41 | Votes7,616 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank06 | Rating / score1,494.04 | Votes617 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank07 | Rating / score1,489.84 | Votes3,484 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank07 | Rating / score1,495.61 | Votes617 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank07 | Rating / score1,496.70 | Votes749 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank07 | Rating / score1,307.29 | Votes3,701 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank07 | Rating / score1,659.26 | Votes9,407 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank07 | Rating / score1,659.26 | Votes9,407 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank07 | Rating / score1,672.48 | Votes6,046 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank08 | Rating / score1,503.75 | Votes14,152 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank08 | Rating / score1,490.65 | Votes7,616 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank08 | Rating / score1,492.52 | Votes3,250 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank08 | Rating / score1,512.51 | Votes14,152 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank08 | Rating / score1,516.50 | Votes12,510 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank08 | Rating / score1,494.75 | Votes19,323 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank08 | Rating / score1,330.28 | Votes1,352 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank09 | Rating / score1,498.83 | Votes1,615 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank09 | Rating / score1,510.72 | Votes7,167 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank09 | Rating / score1,481.07 | Votes11,699 | ObservationsN/A | Result date |
Muse Spark 1.3 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 NanoGPT
- Tracked offerings
- 16
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNanoGPT | Provider model IDmeta/muse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDmeta/muse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDmeta/muse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDmeta/muse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderMeta | Provider model IDmuse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDmeta/muse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderEmpirioLabs AI | Provider model IDmuse-spark-1-3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDmuse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderOpenCode | Provider model IDmuse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderOpper | Provider model IDmuse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDmeta/muse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderRequesty | Provider model IDmuse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderCommandCode | Provider model IDmeta/muse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderEden AI | Provider model IDmeta/muse-spark-1.3 | Regionglobal | Input / 1M$1.25 | Output / 1M$4.25 | Context1M | Updated |
| ProviderAI/ML API | Provider model IDmeta/muse-spark-1.3 | Regionglobal | Input / 1M$1.32 | Output / 1M$4.5 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDmuse-spark-1.3 | Regionglobal | Input / 1M$1.38 | Output / 1M$4.68 | Context1M | Updated |
Muse Spark 1.3 Runtime Performance
Provider-specific output speed and catalog latency for Muse Spark 1.3. 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 1.3 Specifications
Technical details for the model's default version.
- Version
- Muse Spark 1.3
- Released
- Sep 2, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 1M
- Max output
- 943.7K
- Inputs
- audio, image, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Muse Spark 1.3 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 1.3 | Released | LLMBoard88.95 | ParametersN/A | Context1M | Max output943.7K | Open weightsNo | LicenseProprietary |
Models similar to Muse Spark 1.3
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ME
Muse Wonder Full
Meta
ME
Muse Spark 1.1
Meta
ME
Muse Wonder
Meta
ME
Muse Spark 1.2
Meta
ME
Muse Spark Open
Meta
ME
Muse Spark
Meta
What is Muse Spark 1.3?
Key information about Muse Spark 1.3 and its available data.
2 in long-horizon collaboration, multitasking, instruction following, tool use, failure recovery, and concise coding execution. It supports a 1,048,576-token context window and is available through Muse Code and the Meta Model API.
Data as of 2026-10-22.
FAQ
Common questions about Muse Spark 1.3.
When was Muse Spark 1.3 released?
Muse Spark 1.3's default version was released on Sep 2, 2026.
How much does Muse Spark 1.3 cost?
Muse Spark 1.3'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 NanoGPT.
Who created Muse Spark 1.3?
Muse Spark 1.3 was created by Meta.
What is the context window for Muse Spark 1.3?
The default version has a 1M token context window.
Is Muse Spark 1.3 open weight?
No. The default version is not marked as having publicly available weights.