ZMIME
Comparison · 3 models · Updated Nov 22, 2026

Muse Spark 1.3 vs GPT-6 Luna vs GLM-5.3

GPT-6 Luna comes out ahead, 80 to 73 and 64 on our weighted score, and it is the cheaper option too.Muse Spark 1.3 comes out ahead, 86 to 81 and 74 on our weighted score, though GPT-6 Luna is 10× cheaper per token.

  1. Meta

    Muse Spark 1.3

    Released Sep 2, 2026Latest

    73/100
    • ECI158.2
    • Price$1.25 / $4.25
    • Context1.05M
  2. Our pick

    OpenAI

    GPT-6 Luna

    Released Sep 22, 2026Latest

    80/100
    • ECI156.5
    • Price$0.10 / $0.50
    • Context1.05M
  3. Z.ai (Zhipu)

    GLM-5.3

    Released Aug 14, 2026Latest

    64/100
    • ECI157.1
    • Price$1.40 / $4.40
    • Context1M
  4. Our pick

    Meta

    Muse Spark 1.3

    Released Sep 2, 2026Latest

    86/100
    • ECI158.2
    • Price$1.25 / $4.25
    • Context1.05M
  5. OpenAI

    GPT-6 Luna

    Released Sep 22, 2026Latest

    81/100
    • ECI156.5
    • Price$0.10 / $0.50
    • Context1.05M
  6. Z.ai (Zhipu)

    GLM-5.3

    Released Aug 14, 2026Latest

    74/100
    • ECI157.1
    • Price$1.40 / $4.40
    • Context1M
01 — Verdict

GPT-6 Luna is our pickMuse Spark 1.3 is our pick

GPT-6 Luna is the better all-round choice, scoring 80/100 against Muse Spark 1.3 (73) and GLM-5.3 (64). It leads on price. Muse Spark 1.3 wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Muse Spark 1.3 is the better all-round choice, scoring 86/100 against GPT-6 Luna (81) and GLM-5.3 (74). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityMuse Spark 1.3Capabilities Index (ECI): Muse Spark 1.3 158.2 · GLM-5.3 157.1 · GPT-6 Luna 156.5
  • Lowest priceGPT-6 LunaGPT-6 Luna $0.20 · Muse Spark 1.3 $2.00 · GLM-5.3 $2.15 per 1M tokens (3:1 blend)
  • Longest contextGPT-6 Luna and Muse Spark 1.3GPT-6 Luna 1,050,000 · Muse Spark 1.3 1,048,576 · GLM-5.3 1,000,000 tokens
  • Widest inputsMuse Spark 1.3Muse Spark 1.3: Text, Images, PDFs, Audio, Video · GPT-6 Luna: Text, Images, PDFs · GLM-5.3: Text
  • Self-hostingGLM-5.3Publishes downloadable weights
How the score is built
MeasureWeightMuse Spark 1.3GPT-6 LunaGLM-5.3
CapabilityCapabilities Index (ECI)50%868485
Price25%347933
Inputs & features15%1008045
Context window10%656564
Overall100%73/10080/10064/100
How the score is built
MeasureWeightMuse Spark 1.3GPT-6 LunaGLM-5.3
CapabilityCapabilities Index (ECI)67%868485
Inputs & features20%1008045
Context window13%656564
Overall100%86/10081/10074/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

Muse Spark 1.3 vs GPT-6 Luna vs GLM-5.3 specifications side by side
SpecificationMuse Spark 1.3MetaGPT-6 LunaOpenAIGLM-5.3Z.ai (Zhipu)
Capability
Capabilities Index (ECI)158.2 (best)156.5157.1
ECI rank#28 of 159 (best)#38 of 159#34 of 159
ECI confidence interval156.2–160.5154.6–158.5155.0–159.4
ECI evaluation dateSep 2, 2026Sep 22, 2026Aug 14, 2026
Documented capabilitiesMuse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.OpenAI's most efficient model for focused, high-volume tasksFlagship GLM model for long-horizon coding, agents, and complex project delivery
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
GPQA DiamondGraduate-level science questionsNot published90.5%max90.9%max (best)
FrontierMath Tiers 1–3Research-level mathematics74.4%xhigh79.0%max (best)68.8%max
OTIS Mock AIME 2024–2025Competition mathematics99.2%xhigh (best)98.9%max91.1%max
SimpleQA VerifiedShort factual questionsNot published41.4%max (best)41.0%max
Publisher-reported benchmarks
GDPval-AA 2max effort1754EloReported resultSep 2, 2026Not published1769EloReported result
JobBenchmax effort64.9mean rubric scoreReported resultSep 2, 2026Not publishedNot published
OSWorld 2.0 · 08.08max effort66.9mean partial scoreReported resultSep 2, 2026Not publishedNot published
OSWorld 2.0 · 08.08max effort32binary completion rateReported resultSep 2, 2026Not publishedNot published
DeepSearchQAmax effort90.3F1Reported resultSep 2, 2026Not publishedNot published
Agentic IF Index · Meta internalmax effort57.8scoreReported resultSep 2, 2026Not publishedNot published
AutomationBench · public v3 task setmax effort49.6pass@1Reported resultSep 2, 2026Not publishedNot published
MRCR 2 · 8-needle, 256K-512Kmax effort98.5mean sequence-match ratioReported resultSep 2, 2026Not publishedNot published
MRCR 2 · 8-needle, 512K-1Mmax effort98.1mean sequence-match ratioReported resultSep 2, 2026Not publishedNot published
DeepSWE 1.1max effort75.4pass@1Reported resultSep 2, 2026Not publishedNot published
SWE-Atlas Codebase QnAmax effort59.4pass@1Reported resultSep 2, 2026Not publishedNot published
Terminal-Bench 2.1max effort88.8pass@1Reported resultSep 2, 2026Not published88.2pass@1Reported result
DeepSWE 1.1max effortNot published66.6scoreReported resultSep 22, 2026Not published
Terminal-Bench 3.0max effortNot publishedNot published28.3avg@3Reported result
DeepSWE 1.1max effort; 6h timeout; 400K contextNot publishedNot published66.9resolvedReported result
NL2Repomax effortNot publishedNot published58scoreReported result
ProgramBenchmax effortNot publishedNot published19almost solvedReported result
FrontierSWEmax effortNot publishedNot published78.1dominance scoreReported resultAug 14, 2026
SWE-Marathon 1.1max effort; modified anti-cheat checksNot publishedNot published42.5scoreReported result
PostTrainBenchmax effort; 3 runs; modified external-API checksNot publishedNot published39.8weighted averageReported result
CyberGymmax effortNot publishedNot published84.5pass@1Reported result
ExploitGym · 869 tasksmax effort; 2h rescaled timeoutNot publishedNot published105tasks solvedReported result
ExploitGym · 869 tasksmax effort; 6h rescaled timeoutNot publishedNot published130tasks solvedReported result
ExploitBenchmax effort; union over 3 revisionsNot publishedNot published54.4average coverageReported result
Toolathlon-Verifiedmax effortNot publishedNot published73pass@1Reported result
AutomationBench 1.0.6max effortNot publishedNot published48.2pass@1Reported result
Agents' Last Exammax effort; CLINot publishedNot published28.5scoreReported result
Humanity's Last Exammax effort; with toolsNot publishedNot published62.5accuracyReported result
Price per million tokens
Input$1.25$0.10 (best)$1.40
Output$4.25$0.50 (best)$4.40
Cached input$0.15$0.01 (best)$0.26
Blended (3:1)$2.00$0.20 (best)$2.15
Long-context rateSame rateOver 272K: $0.20 / $0.75Same rate
Price sourceOfficial Meta APIOfficial OpenAI APIOfficial Z.AI API
Limits
Context window1,048,576 tokens1,050,000 tokens (best)1,000,000 tokens
Max inputNot published922,000 tokensNot published
Max output131,072 tokens (best)128,000 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsYesYesNo
AudioYesNoNo
VideoYesNoNo
ReasoningYesminimal · low · medium · high · xhigh · maxYeslow · medium · high · xhigh · maxYeslow · high · max
Tool callingYesYesYes
Structured outputYesYesYes
File attachmentsYesYesNo
Temperature controlYesYesYes
Reasoning controleffortefforteffort
Availability
WeightsProprietaryProprietaryOpen
API model IDmuse-spark-1.3gpt-6-lunaglm-5.3
API providers1849123 (best)
ReleasedSep 2, 2026Sep 22, 2026Aug 14, 2026
Knowledge cutoffNot publishedMay 18, 2026Not published
Publisher documentationPublisher documentationPublisher documentationPublisher documentation · Model weights
Source metadata updatedSep 2, 2026Sep 22, 2026Aug 14, 2026
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026Nov 22, 2026
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Muse Spark 1.3$21.00
  • GPT-6 Luna$2.00
  • GLM-5.3$22.80
04 — Questions

Which should you choose?

Which is better: Muse Spark 1.3, GPT-6 Luna or GLM-5.3?

GPT-6 Luna is the better all-round choice, scoring 80/100 against Muse Spark 1.3 (73) and GLM-5.3 (64). It leads on price. Muse Spark 1.3 wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Muse Spark 1.3 is the better all-round choice, scoring 86/100 against GPT-6 Luna (81) and GLM-5.3 (74). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, Muse Spark 1.3, GPT-6 Luna or GLM-5.3?

GPT-6 Luna is cheaper at $0.10 input / $0.50 output per million tokens (official OpenAI API price). Muse Spark 1.3 costs $1.25 input / $4.25 output per million tokens (official Meta API price); GLM-5.3 costs $1.40 input / $4.40 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $0.20 per million tokens for GPT-6 Luna versus $2.00 for Muse Spark 1.3 (10× as much) and $2.15 for GLM-5.3 (11× as much).

Which scores higher on benchmarks?

Muse Spark 1.3 scores higher on the Capabilities Index (ECI): Muse Spark 1.3 158.2 (#28 of 159), GLM-5.3 157.1 (#34 of 159) and GPT-6 Luna 156.5 (#38 of 159). The confidence ranges of the top two overlap (156.2–160.5 vs 155.0–159.4), so treat the gap as small. On individual benchmarks: FrontierMath Tiers 1–3 — GPT-6 Luna 79.0%, Muse Spark 1.3 74.4%, GLM-5.3 68.8%; OTIS Mock AIME 2024–2025 — Muse Spark 1.3 99.2%, GPT-6 Luna 98.9%, GLM-5.3 91.1%.

Which is better for coding?

There are no published SWE-bench Verified results for Muse Spark 1.3, GPT-6 Luna and GLM-5.3 yet, so there is no like-for-like coding score. On overall capability, Muse Spark 1.3 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Which has the bigger context window?

GPT-6 Luna and Muse Spark 1.3 have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for GLM-5.3. Maximum output per response: Muse Spark 1.3 up to 131,072, GPT-6 Luna up to 128,000, GLM-5.3 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Muse Spark 1.3 accepts text, images, PDFs, audio and video; GPT-6 Luna accepts text, images and PDFs; GLM-5.3 accepts text. Muse Spark 1.3 handles the widest range of inputs.

Are any of these open source?

GLM-5.3 publishes its weights and can be self-hosted; Muse Spark 1.3 and GPT-6 Luna is proprietary.

Which is newer?

GPT-6 Luna is the newest, released Sep 22, 2026. Muse Spark 1.3 came out Sep 2, 2026; GLM-5.3 came out Aug 14, 2026. Knowledge cutoff: GPT-6 Luna May 18, 2026.

How do you decide the winner?

This rating uses capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.