BenchLeader

GLM 5.2 vs Muse Spark

Full profiles: GLM 5.2 (Zhipu AI) and Muse Spark (Meta): every benchmark, price and rank.

Updated · Data from 9 sources

As of 16 Nov 2026, GLM 5.2 and Muse Spark are neck and neck on quality (58.9 vs 64.2 on the BenchLeader Index, inside the ±5.3 margin). Muse Spark leads in every category we measure both in.

Key facts (as of 16 Nov 2026)

  • GLM 5.2 scores 58.9 on the BenchLeader Index and Muse Spark scores 64.2 (BenchLeader, 16 Nov 2026).
  • GLM 5.2 costs $2.15 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 25 benchmarks both models have, GLM 5.2 leads 18 (BenchLeader, 16 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingMuse Spark65 vs 62 category score; SciCode 51.5% vs 51.2%Medium
Agents & tool useMuse Spark65 vs 62 category score; Terminal-Bench Hard 45.5% vs 50.8%Medium
MathsMuse Spark59 vs 53 category score; OTIS Mock AIME 88.9% vs 86.4%Medium
ReasoningMuse Spark67 vs 57 category score; Arena Hard Prompts 1506 vs 1496High
KnowledgeMuse Spark63 vs 44 category scoreHigh
Long documentsEither64 vs 64 category score; AA-LCR v1.1 78.3% vs 78.0%Either
Following instructionsMuse Spark77 vs 72 category score; IFBench 75.9% vs 73.3%Medium
Chat quality (human preference)Muse Spark68 vs 66 on Arena votesMedium
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • GLM 5.2 (max) and Muse Spark are neck and neck on quality (58.9 vs 64.2, within the ±5.3 margin).
  • GLM 5.2 (max) is stronger in long context.
  • Muse Spark is stronger in agents & tools, coding, human preference, instruction following, knowledge, maths, reasoning.

At a glance

SpecGLM 5.2Muse Spark
DeveloperZhipu AIMeta
Released16 Jun 20268 Apr 2026
Context window (tokens)1,000,000262,144
Compared atGLM 5.2 (max)Muse Spark
Open weightsYesNo
Price in / out / cached input per 1M$1.40 / $4.40 / $0.260–

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGLM 5.2 (max)Muse SparkLeader
Reasoning57.267.4Muse Spark
Coding61.865.1Muse Spark
Agents & tools62.165.0Muse Spark
Maths52.659.1Muse Spark
Knowledge44.363.1Muse Spark
Instruction following71.876.9Muse Spark
Human preference66.468.1Muse Spark
Multimodal–64.2not comparable
Long context63.863.6level

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsMathsKnowledgeInstructionfollowingLong contextHumanpreferenceGLM 5.2, Reasoning: 57.2GLM 5.2, Coding: 61.8GLM 5.2, Agents & tools: 62.1GLM 5.2, Maths: 52.6GLM 5.2, Knowledge: 44.3GLM 5.2, Instruction following: 71.8GLM 5.2, Long context: 63.8GLM 5.2, Human preference: 66.4Muse Spark, Reasoning: 67.4Muse Spark, Coding: 65.1Muse Spark, Agents & tools: 65.0Muse Spark, Maths: 59.1Muse Spark, Knowledge: 63.1Muse Spark, Instruction following: 76.9Muse Spark, Long context: 63.6Muse Spark, Human preference: 68.1

Not drawn, measured for fewer than two of these models: Multimodal.

Model, click to add or removeIndex

Where sources disagree

Across the 25 benchmarks both have, GLM 5.2 leads 18, Muse Spark leads 7. Every overall index that rates both puts Muse Spark ahead.

Overall indexGLM 5.2 (max)Muse SparkLeader
BenchLeader Index58.964.2neck and neck
Arena Text14751489Muse Spark

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGLM 5.2 (max)Muse Spark
Blended price per 1M tokens$2.15–
Input / output per 1M$1.40 / $4.40– / –
Cached input per 1M$0.260–
Price per task: chat reply$0.0019–
Price per task: summarize a 30-page report$0.019–
Price per task: code edit$0.015–
Price per task: agentic coding session$0.102–
Price per task: structured extraction$0.0037–
Agentic coding session, input mostly cached$0.050–
Output speed69 tok/s–
Time to first answer26.8 s–
Time to a complete answer, last measured 13 Nov 202656.7 s–

Each model is compared at its best-ranked reasoning-effort setting. GLM 5.2 (max) scores 58.9 and takes 27 s to its first answer token; GLM 5.2 scores 51.9 in 1 s, GLM 5.2 (no reasoning) scores 45.8 in 2 s. Muse Spark scores 64.2. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

126 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGLM 5.2 (max)Muse Spark
BenchLeader IndexBenchLeader58.964.2
Agents & tools scoreBenchLeader62.165.0
Coding scoreBenchLeader61.865.1
Human preference scoreBenchLeader66.468.1
Instruction following scoreBenchLeader71.876.9
Knowledge scoreBenchLeader44.363.1
Long context scoreBenchLeader63.863.6
Maths scoreBenchLeader52.659.1
Reasoning scoreBenchLeader57.267.4
Multimodal scoreBenchLeader–64.2
Blended price $/MBenchLeader$2.15–
Output speedBenchLeader69 tok/s–
Time to first answerBenchLeader26.8 s–
Context windowBenchLeader1,000,000 tokens262,144 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub91.9%89.8%
Humanity's Last ExamScale AI / CAIS–40.6%
SimpleBenchSimpleBench58.8%†–
Arena Hard PromptsArena (LMArena)14961506
LiveBench 1.0 ReasoningLiveBench78.6%†–
GPQA Diamond (AA)Artificial Analysis89.5%88.4%
Humanity's Last Exam (AA)Artificial Analysis41.1%40.7%
HLE-Diamond (AA)Artificial Analysis17.7%–
GPQA Diamond (Vals)Vals AI85.6%†89.7%
Kagi LLM BenchmarkKagi LLM Benchmark62.6%†–
ARC-AGI-1ARC Prize77.0%†–
ARC-AGI-2ARC Prize22.8%†–
CritPtArtificial Analysis20.9%11.3%
Arena ExpertArena (LMArena)15021491
Chess PuzzlesEpoch AI Benchmarking Hub22.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub18.0%†–
LMCAEpoch AI Benchmarking Hub45.8%–
DTBenchEpoch AI Benchmarking Hub93.6%–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub78.7%–
SciCodeSciCode51.2%51.5%
WeirdMLWeirdML70.1%–
FrontierCodeCognition24.5%†–
Arena CodingArena (LMArena)15151529
Arena WebDevArena (LMArena)1608–
LiveBench 1.0 CodingLiveBench79.7%†–
Show all 126 benchmarks
MetricPublisherGLM 5.2 (max)Muse Spark
Coding
SciCode (AA)Artificial Analysis51.2%–
LiveCodeBenchVals AI69.5%†–
SWE-bench (Vals)Vals AI82.8%74.4%
SWE-Bench ProScale AI SEAL–55.0%
Code MigrationVals AI37.9%–
ProgramBenchVals AI0.5%–
Vibe Code Bench v1.1Vals AI64.0%19.7%
SWE-Bench Pro (private)Scale AI SEAL–44.7%
SWE Atlas v1.0: Codebase QnAScale AI SEAL48.1%†24.2%
SWE Atlas v1.0: RefactoringScale AI SEAL42.4%†–
SWE Atlas v1.0: Test WritingScale AI SEAL41.5%†31.1%
MirrorCodeEpoch AI Benchmarking Hub36.7%–
Surface Evolver BenchEpoch AI Benchmarking Hub55.6%†–
DeepSWE v1.1Epoch AI Benchmarking Hub43.8%–
ALE-BenchEpoch AI Benchmarking Hub1010.2–
Terminal-Bench 4.0 (AA)Artificial Analysis1.0%–
Terminal-Bench 2.1 (AA)Artificial Analysis77.9%62.2%
Startrise FrontendStartrise72.1%†–
GameBench 2 OverallDuelLab GameBench 243.1†–
GameBench 2 by reasoning settingDuelLab GameBench 232.4†–
Design Arena WebsiteDesign Arena1277†1253
Agents & tools
APEX-AgentsMercor45.2%†–
Arena AgentArena (LMArena)0.2–
LiveBench Agentic CodingLiveBench51.8%†–
Terminal-Bench HardArtificial Analysis50.8%45.5%
τ²-Bench Telecom (AA)Artificial Analysis99.1%91.5%
Terminal-Bench 2.1 (Vals)Vals AI67.8%–
MCP AtlasScale AI SEAL77.8%†82.2%
HiL-BenchScale AI SEAL43.7%†–
τ³-bench Bankingτ²-bench37.1%†–
GDPval-AA v2.1Artificial Analysis13801006
τ³-Banking (AA)Artificial Analysis34.6%–
ITBench SRE (AA)Artificial Analysis42.7%–
APEX-Agents (AA)Artificial Analysis33.7%–
Finance Agent v2Vals AI49.7%†–
Harvey's Legal Agent Benchmark v1Vals AI7.1%–
Legal Research BenchVals AI31.3%–
SkillsBenchVals AI45.1%–
SREBenchVals AI0.0%–
Terminal-Bench 2.0 (Vals)Vals AI–59.5%
Arena Agent Task CompletionArena (LMArena)1.7–
PostTrainBenchEpoch AI Benchmarking Hub30.4%–
GBAEvalEpoch AI Benchmarking Hub0.0%†–
Vending-Bench 2Andon Labs8313.8†–
AutomationBenchArtificial Analysis28.4%–
GDP.pdf (AA)Artificial Analysis10.4%–
EnterpriseOps-GymArtificial Analysis42.7%–
AA-Briefcase v1.1Artificial Analysis1226646
Design Arena AgenticDesign Arena1194†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub59.2%–
FrontierMath Tier 4Epoch AI Benchmarking Hub29.3%–
OTIS Mock AIMEEpoch AI Benchmarking Hub86.4%88.9%
ProofBenchVals AI35.0%17.0%
LiveBench MathematicsLiveBench89.8%†–
AIME (Vals)Vals AI–96.9%
AIME 2026MathArena90.0%–
HMMT February 2026MathArena92.4%–
MathArena ApexMathArena19.8%–
Arena MathsArena (LMArena)14871469
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub34.2%–
LiveBench 1.0 Data AnalysisLiveBench73.7%†–
AA-Omniscience v1.1Artificial Analysis0.6–
MMLU-ProVals AI86.7%†87.3%
LegalBenchVals AI84.1%†84.2%
CorpFinVals AI66.1%†65.1%
TaxEvalVals AI73.3%†77.7%
PRBench FinanceScale AI SEAL–52.4%
PRBench LegalScale AI SEAL–52.3%
MultiNRCScale AI SEAL–59.0%
CaseLaw v2Vals AI–63.1%
Excel Modeling BenchmarkVals AI61.5%†–
MedCodeVals AI40.8%†51.3%
MedScribeVals AI83.5%†85.9%
DrugDiscoveryBenchScale AI SEAL36.2%†–
EBR-benchEpoch AI Benchmarking Hub9.5%–
AA-Omniscience v1.1: accuracyArtificial Analysis21.1%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis74.1%–
Instruction following
LiveBench LanguageLiveBench76.2%†–
LiveBench Instruction FollowingLiveBench62.3%†–
IFBenchArtificial Analysis73.3%75.9%
MultiChallengeScale AI SEAL–75.5%
TutorBenchScale AI SEAL–68.5%
Arena Instruction FollowingArena (LMArena)14701465
Human preference
Arena TextArena (LMArena)14751489
EQ-Bench 4EQ-Bench1208†–
EQ-Bench Creative Writing v3EQ-Bench1759†–
Arena Creative WritingArena (LMArena)14511464
Arena Multi-turnArena (LMArena)14771493
Arena Longer QueriesArena (LMArena)14861476
Multimodal
Arena VisionArena (LMArena)–1306
MMMU-ProArtificial Analysis–80.5%
MMMU-Pro (Vals)Vals AI–87.4%
Long context
AA-LCR v1.1Artificial Analysis78.3%78.0%
Arena DocumentArena (LMArena)–1467
MLCRArtificial Analysis12.8%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub153.0†153.1
LiveBench 1.0LiveBench73.2%†–
AA Intelligence Index v4.3.2Artificial Analysis33.731.3
AA Progress Index v1Artificial Analysis302.5289.1
Safety & honesty
FORTRESSScale AI SEAL48.7%†20.2%
Metadata
AA Openness IndexArtificial Analysis44.4–

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GLM 5.2 (max): 1 new result (GDPval-AA v2.1).
  • Muse Spark: 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1).
  • GLM 5.2 (max): BenchLeader Index 59.5 → 59.0.
  • GLM 5.2 (max): 3 new results (AIME 2026, HMMT February 2026, MathArena Apex); 1 score revision.
  • GLM 5.2 (max): 1 new result (MirrorCode).
  • GLM 5.2 (max): BenchLeader Index 60.2 → 59.5.
  • Muse Spark: BenchLeader Index 64.6 → 64.1.
  • GLM 5.2 (max): 4 new results (HLE-Diamond (AA), AA-Omniscience v1.1, AA-Omniscience v1.1: accuracy…).
  • Muse Spark: 1 score revision.
  • GLM 5.2 (max): cached input price moved from $0.30/M to $0.26/M (13% down).

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

GLM 5.2 vs Muse Spark: questions

Is GLM 5.2 better than Muse Spark?
GLM 5.2 (max) and Muse Spark are neck and neck on quality (58.9 vs 64.2, within the ±5.3 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
Is GLM 5.2 or Muse Spark better for coding?
Muse Spark scores higher in coding (65 vs 62 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 51.2% for GLM 5.2 against 51.5% for Muse Spark.
Is GLM 5.2 or Muse Spark better for agents and tool use?
Muse Spark scores higher in agentic tasks (65 vs 62 on the category index, where 50 is average). On Terminal-Bench Hard, the top shared agents & tools benchmark, it is 50.8% for GLM 5.2 against 45.5% for Muse Spark.
Which is better for long documents?
They are level on long-context benchmarks (64 vs 64). GLM 5.2 accepts more context: 1,000,000 against 262,144 tokens for Muse Spark.
Do independent benchmarks agree on GLM 5.2 vs Muse Spark?
Across the 25 benchmarks both have, GLM 5.2 leads 18, Muse Spark leads 7. Every overall index that rates both puts Muse Spark ahead.
More questions (1)
When was GLM 5.2 released?
GLM 5.2 was released on 16 Jun 2026.