Skip to main content
BenchLM
Advertise

Model profile

Muse Spark 1.1

MetaCurrentReleased Jul 9, 2026
Data verified
Overall Score
77.44Public #6 of 200Verified #6 of 99
Arena Elo
1495
Eligible category ranks
3of 8
Price (1M tokens)
Not listedAPI pricing
Speed
Not listed
Context
1M

Evidence coverage

39 of 323 tracked benchmarks are published. 21 are verified and 18 provisional. 5 of 8 categories are measured.

Updated July 23, 2026Methodology
Published / tracked
39 / 323
Verified
21
Provisional
18
Categories with evidence
5 / 8

Evidence by category

  • Agentic20 benchmarks
    Mixed evidence
  • Coding4 benchmarks
    Mixed evidence
  • Reasoning3 benchmarks
    Mixed evidence
  • Knowledge9 benchmarks
    Mixed evidence
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal3 benchmarks
    Mixed evidence
  • Inst. Following0 benchmarks
    Not measured
ProprietaryReasoning
Confidence:
Medium
1.1

Muse Spark 1.1 ranks #6 out of 200 models on the public leaderboard with an overall score of 77.44/100. It also ranks #6 out of 99 on the verified leaderboard. This places it in the upper tier of AI models, with competitive scores across most benchmark categories.

Muse Spark 1.1 is a proprietary model with a 1M token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

Muse Spark 1.1 sits inside the Muse Spark family alongside Muse Spark. BenchLM links it directly to Muse Spark as the earlier related model in that lineage. This profile currently has 39 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Knowledge (#1), while its weakest is Coding (#11). This performance profile makes it particularly effective for knowledge-intensive tasks like research, analysis, and factual Q&A.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 73.51–81.96

  1. GPT-5.6 Sol
    OpenAI
    #381.96
    GPT-5.6 Sol is #3 with a score of 81.96.
    Compare
  2. Kimi K3
    Moonshot AI
    #480.96
    Kimi K3 is #4 with a score of 80.96.
    Compare
  3. Claude Opus 4.8
    Anthropic
    #578.34
    Claude Opus 4.8 is #5 with a score of 78.34.
    Compare
  4. Muse Spark 1.1Current model
    Meta
    #677.44
    Muse Spark 1.1 is #6 with a score of 77.44.
  5. Grok 4.5
    xAI
    #776.72
    Grok 4.5 is #7 with a score of 76.72.
    Compare
  6. GPT-5.4
    OpenAI
    #874.24
    GPT-5.4 is #8 with a score of 74.24.
    Compare
  7. GPT-5.5
    OpenAI
    #973.51
    GPT-5.5 is #9 with a score of 73.51.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Knowledge100%
    Eligible cohort rank #1 of 52Category score 93.5
  2. Agentic98%
    Eligible cohort rank #3 of 119Category score 68.6
  3. Coding92%
    Eligible cohort rank #11 of 122Category score 65.1

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #3 of 119Percentile 98thWeight 22%20 benchmarksMixed sources68.6
CodingRank #11 of 122Percentile 92ndWeight 20%4 benchmarksMixed sources65.1
ReasoningWeight 17%3 benchmarksMixed sourcesScore pending
KnowledgeRank #1 of 52Percentile 100thWeight 12%9 benchmarksMixed sources93.5
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank Not rankedWeight 12%3 benchmarksMixed sources79.1
Inst. FollowingWeight 5%0 benchmarksNot measuredNot measured

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1495±7.57,074
Coding1533±13.52,087
Math1481±32.6320
Instruction Following1478±12.42,443
Creative Writing1459±17.21,278
Multi-turn1505±18.01,199
Hard Prompts1514±9.14,692
Hard Prompts (English)1518±13.91,901
Longer Query1484±11.13,145

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic20 benchmarks
Terminal-Bench 2.0Provider exact
80%Weighted 38%
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
OSWorld-VerifiedProvider exact
80.8%Weighted 34%
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
MCP AtlasProvider exact
88.1%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
ToolathlonProvider exact
75.6%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
DeepSearchQAProvider exact
84.9%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
CyberGymProvider exact
59.0%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
Finance Agent v2Provider exact
57.2%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
deepSweProvider exact
53.3%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
OSWorld 2.0Provider exact
14.2%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Meta reports Muse Spark 1.1 on OSWorld 2.0 in the Muse Spark 1.1 evaluation report. BenchLM stores the exact published value as display-only unless the benchmark is part of the weighted schema.
JobBenchProvider exact
54.7%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Meta reports Muse Spark 1.1 on JobBench in the Muse Spark 1.1 evaluation report. BenchLM stores the exact published value as display-only unless the benchmark is part of the weighted schema.
CybenchProvider exact
92.9%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Meta reports Muse Spark 1.1 on Cybench in the Muse Spark 1.1 evaluation report. BenchLM stores the exact published value as display-only unless the benchmark is part of the weighted schema.
ExploitGymProvider exact
0.8%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Meta reports Muse Spark 1.1 on ExploitGym in the Muse Spark 1.1 evaluation report. BenchLM stores the exact published value as display-only unless the benchmark is part of the weighted schema.
AA Agentic IndexReported

Artificial Analysis Agentic Index

37.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAReported

GDPval-AA normalized

43.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAProvider exact
1374Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
AA BriefcaseReported

Artificial Analysis Briefcase

863Display only
Source: Artificial Analysis: aa-briefcase leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA AutomationBenchReported

Artificial Analysis AutomationBench

42.8%Display only
Source: Artificial Analysis: automationbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Harvey LABReported

Artificial Analysis Harvey LAB-AA

93.1%Display only
Source: Artificial Analysis: harvey-lab-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Tau3 BankingReported

Artificial Analysis Tau3-Banking

25.2%Display only
Source: Artificial Analysis: tau3-banking leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
aaTerminalBench21Reported
77.9%Display only
Source: Artificial Analysis: terminalbench-v2-1 leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Coding4 benchmarks
SWE-bench ProProvider exact
61.5%Weighted 10%
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
Terminal-Bench 2.0Provider exact
80.0%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
AA Coding IndexReported

Artificial Analysis Coding Index

71.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-SciCodeReported

Artificial Analysis SciCode

58.2%Display only
Source: Artificial Analysis: scicode leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Reasoning3 benchmarks
MRCR 1MProvider exact
54.1%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
AA-LCRReported

Artificial Analysis Long Context Reasoning

63.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

15.1%Display only
Source: Artificial Analysis: critpt leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Knowledge9 benchmarks
HLEProvider exact

Humanity's Last Exam

62.1%Weighted 45%
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
HLE w/o toolsProvider exact

Humanity's Last Exam without tools

52.2%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
HealthBench ProfessionalProvider exact
59.3%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Meta reports Muse Spark 1.1 on HealthBench Professional in the Muse Spark 1.1 evaluation report. BenchLM stores the exact published value as display-only unless the benchmark is part of the weighted schema.
Artificial Analysis Intelligence IndexReported
50.6%Display only
Source: Artificial Analysis: artificial-analysis-intelligence-index leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

89.8%Display only
Source: Artificial Analysis: gpqa-diamond leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

45.1%Display only
Source: Artificial Analysis: humanitys-last-exam leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

18.0%Display only
Source: Artificial Analysis: omniscience leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

40.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

38.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Multimodal3 benchmarks
CharXivProvider exact

CharXiv Reasoning

88.4%Weighted 25%
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
BabyVisionProvider exact
76.3%Display only
Source: Meta AI: Muse Spark 1.1 evaluation reportProvenance: Provider exact
Design Arena WebsiteReported

Design Arena Website Elo

1299Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.

Muse Spark Family

1.1 · 1.1

Related Earlier Model

Muse Spark
Muse SparkScore 71.04

Frequently Asked Questions

How does Muse Spark 1.1 perform overall in AI benchmarks?

Muse Spark 1.1 currently ranks #6 out of 200 models on BenchLM's provisional leaderboard with an overall score of 77.44. It also ranks #6 out of 99 on the verified leaderboard. It is created by Meta. Its published context window is 1M.

Is Muse Spark 1.1 good for knowledge and understanding?

Muse Spark 1.1 ranks #1 out of 52 models in knowledge and understanding benchmarks with an average score of 93.5. It is among the top performers in this category.

Is Muse Spark 1.1 good for coding and programming?

Muse Spark 1.1 ranks #11 out of 122 models in coding and programming benchmarks with an average score of 65.1. There are stronger options in this category.

Is Muse Spark 1.1 good for reasoning and logic?

Muse Spark 1.1 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Muse Spark 1.1 good for agentic tool use and computer tasks?

Muse Spark 1.1 ranks #3 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 68.6. It is among the top performers in this category.

Is Muse Spark 1.1 good for multimodal and grounded tasks?

Muse Spark 1.1 has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Which sibling models are related to Muse Spark 1.1?

Muse Spark 1.1 belongs to the Muse Spark family. Related variants on BenchLM include Muse Spark.

Does Muse Spark 1.1 have full benchmark coverage on BenchLM?

Not yet. Muse Spark 1.1 currently has 39 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Muse Spark 1.1?

Muse Spark 1.1 has a published context window of 1M, which determines how much text it can process in a single interaction.

Related Resources

More from Meta LLM Pricing Comparison BenchLM Methodology The AI Race Which LLM Should I Use? Benchmark Explainers
Last updated: July 23, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.