ZMIME
Comparison · 3 models · Updated Nov 22, 2026

DeepSeek V4.1 Flash vs GPT-5.6 Luna vs Muse Spark 1.3

Too close to call on our weighted score (DeepSeek V4.1 Flash 76, GPT-5.6 Luna 76, Muse Spark 1.3 68). The right pick depends on what you value most.Too close to call on our weighted score (Muse Spark 1.3 82, DeepSeek V4.1 Flash 81, GPT-5.6 Luna 81). The right pick depends on what you value most.

  1. DeepSeek

    DeepSeek V4.1 Flash

    Released Sep 10, 2026

    76/100
    • ECI157.0
    • Price$0.222 / $1.04
    • Context1M
  2. OpenAI

    GPT-5.6 Luna

    Released Jul 9, 2026

    76/100
    • ECI156.7
    • Price$0.20 / $1.20
    • Context1.05M
  3. Meta

    Muse Spark 1.3

    Released Sep 2, 2026Latest

    68/100
    • ECI158.2
    • Price$1.25 / $4.25
    • Context1.05M
  4. DeepSeek

    DeepSeek V4.1 Flash

    Released Sep 10, 2026

    81/100
    • ECI157.0
    • Price$0.222 / $1.04
    • Context1M
  5. OpenAI

    GPT-5.6 Luna

    Released Jul 9, 2026

    81/100
    • ECI156.7
    • Price$0.20 / $1.20
    • Context1.05M
  6. Meta

    Muse Spark 1.3

    Released Sep 2, 2026Latest

    82/100
    • ECI158.2
    • Price$1.25 / $4.25
    • Context1.05M
01 — Verdict

Too close to call

It is close. Our weighted score puts them within a point (DeepSeek V4.1 Flash 76/100, GPT-5.6 Luna 76/100, Muse Spark 1.3 68/100), so choose by what matters most for your work: Muse Spark 1.3 for raw capability and DeepSeek V4.1 Flash on price. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within 1 points (Muse Spark 1.3 82/100, DeepSeek V4.1 Flash 81/100, GPT-5.6 Luna 81/100), so choose by what matters most for your work: Muse Spark 1.3 for raw capability and DeepSeek V4.1 Flash on price. The score weighs capability 83%, context window 17%.

  • CapabilityMuse Spark 1.3Capabilities Index (ECI): Muse Spark 1.3 158.2 · DeepSeek V4.1 Flash 157.0 · GPT-5.6 Luna 156.7
  • Lowest priceDeepSeek V4.1 FlashDeepSeek V4.1 Flash $0.426 · GPT-5.6 Luna $0.45 · Muse Spark 1.3 $2.00 per 1M tokens (3:1 blend)
  • Longest contextGPT-5.6 Luna and Muse Spark 1.3GPT-5.6 Luna 1,050,000 · Muse Spark 1.3 1,048,576 · DeepSeek V4.1 Flash 1,000,000 tokens
  • Widest inputsMuse Spark 1.3DeepSeek V4.1 Flash: Text, Images · GPT-5.6 Luna: Text, Images, PDFs · Muse Spark 1.3: Text, Images, PDFs, Audio, Video
  • Self-hostingDeepSeek V4.1 FlashPublishes downloadable weights (MIT)
How the score is built
MeasureWeightDeepSeek V4.1 FlashGPT-5.6 LunaMuse Spark 1.3
CapabilityCapabilities Index (ECI)59%848486
Price29%656334
Context window12%646565
Overall100%76/10076/10068/100

Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.

How the score is built
MeasureWeightDeepSeek V4.1 FlashGPT-5.6 LunaMuse Spark 1.3
CapabilityCapabilities Index (ECI)83%848486
Context window17%646565
Overall100%81/10081/10082/100

Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.

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.

DeepSeek V4.1 Flash vs GPT-5.6 Luna vs Muse Spark 1.3 specifications side by side
SpecificationDeepSeek V4.1 FlashDeepSeekGPT-5.6 LunaOpenAIMuse Spark 1.3Meta
Capability
Capabilities Index (ECI)157.0156.7158.2 (best)
ECI rank#35 of 159#37 of 159#28 of 159 (best)
ECI confidence interval155.1–159.2154.9–158.8156.2–160.5
ECI evaluation dateSep 9, 2026Jul 9, 2026Sep 2, 2026
Documented capabilitiesDeepSeek V4.1 Flash model for reasoning and agentic codingCost-efficient GPT-5.6 model for fast, high-volume workloadsMuse 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.
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
GPQA DiamondGraduate-level science questions89.8%max91.6%max (best)Not published
FrontierMath Tiers 1–3Research-level mathematics67.4%max82.1%max (best)74.4%xhigh
OTIS Mock AIME 2024–2025Competition mathematics98.3%max98.3%max99.2%xhigh (best)
SimpleQA VerifiedShort factual questions42.9%max (best)41.0%maxNot published
Publisher-reported benchmarks
GPQA Diamondreasoning_effort=10090.9pass@1Reported resultNot publishedNot published
MathArena Apexreasoning_effort=10065.6pass@1Reported resultNot publishedNot published
Humanity's Last Exam · full setreasoning_effort=10036.8pass@1Reported resultNot publishedNot published
Humanity's Last Exam · text-only subsetreasoning_effort=10039.1pass@1Reported resultNot publishedNot published
Codeforcesreasoning_effort=1003471ratingReported resultNot publishedNot published
Terminal-Bench 2.1reasoning_effort=10090.6pass@1Reported resultNot publishedNot published
Terminal-Bench 3.0reasoning_effort=10030pass@1Reported resultNot publishedNot published
Terminal-Bench 4.0reasoning_effort=10031.2pass@1Reported resultNot publishedNot published
DeepSWE 1.1reasoning_effort=10074.2resolvedReported resultNot publishedNot published
ProgramBenchreasoning_effort=10020.3almost@1Reported resultNot publishedNot published
NL2Reporeasoning_effort=10064scoreReported resultNot publishedNot published
CyberGymreasoning_effort=10088.1pass@1Reported resultNot publishedNot published
ExploitGymreasoning_effort=10015.3pass@1Reported resultNot publishedNot published
AutomationBenchreasoning_effort=10054.8pass@1Reported resultNot publishedNot published
Agents' Last Examreasoning_effort=10031.8pass@1Reported resultNot publishedNot published
SEC-Bench Proreasoning_effort=10062.8pass@1Reported resultNot publishedNot published
Humanity's Last Examreasoning_effort=100; with tools63.9pass@1Reported resultNot publishedNot published
Chartographyreasoning_effort=100; with tools78.9pass@1Reported resultNot publishedNot published
BabyVisionreasoning_effort=100; with tools89.6pass@1Reported resultNot publishedNot published
ZeroBench · mainreasoning_effort=100; with tools49pass@5Reported resultNot publishedNot published
SWE-Bench ProPublisher-reported resultNot published62.7resolve rateReported resultJul 9, 2026Not published
Terminal-Bench 2.1Publisher-reported resultNot published84.7success rateReported resultJul 9, 2026Not published
DeepSWE 1.1Publisher-reported resultNot published67.2resolve rateReported resultJul 9, 2026Not published
GPQA DiamondPublisher-reported resultNot published92.3accuracyReported resultJul 9, 2026Not published
FrontierMath v2 · Tier 1-3Publisher-reported resultNot published78.6accuracyReported resultJul 9, 2026Not published
BrowseCompPublisher-reported resultNot published83.3accuracyReported resultJul 9, 2026Not published
OSWorld 2.0Publisher-reported resultNot published45.6success rateReported resultJul 9, 2026Not published
MMMU Prono toolsNot published78.4accuracyReported resultJul 9, 2026Not published
Agents' Last ExamPublisher-reported resultNot published50.3Reported resultJul 9, 2026Not published
ToolathlonPublisher-reported resultNot published53.4success rateReported resultJul 9, 2026Not published
Artificial Analysis Intelligence Index 4.1maxNot published51.2index scoreReported resultJul 9, 2026Not published
Artificial Analysis Coding Agent Index 1.1maxNot published74.6index scoreReported resultJul 9, 2026Not published
GDPval-AA 2max effortNot publishedNot published1754EloReported resultSep 2, 2026
JobBenchmax effortNot publishedNot published64.9mean rubric scoreReported resultSep 2, 2026
OSWorld 2.0 · 08.08max effortNot publishedNot published66.9mean partial scoreReported resultSep 2, 2026
OSWorld 2.0 · 08.08max effortNot publishedNot published32binary completion rateReported resultSep 2, 2026
DeepSearchQAmax effortNot publishedNot published90.3F1Reported resultSep 2, 2026
Agentic IF Index · Meta internalmax effortNot publishedNot published57.8scoreReported resultSep 2, 2026
AutomationBench · public v3 task setmax effortNot publishedNot published49.6pass@1Reported resultSep 2, 2026
MRCR 2 · 8-needle, 256K-512Kmax effortNot publishedNot published98.5mean sequence-match ratioReported resultSep 2, 2026
MRCR 2 · 8-needle, 512K-1Mmax effortNot publishedNot published98.1mean sequence-match ratioReported resultSep 2, 2026
DeepSWE 1.1max effortNot publishedNot published75.4pass@1Reported resultSep 2, 2026
SWE-Atlas Codebase QnAmax effortNot publishedNot published59.4pass@1Reported resultSep 2, 2026
Terminal-Bench 2.1max effortNot publishedNot published88.8pass@1Reported resultSep 2, 2026
Price per million tokens
Input$0.222$0.20 (best)$1.25
Output$1.04 (best)$1.20$4.25
Cached inputNot published$0.02 (best)$0.15
Blended (3:1)$0.426 (best)$0.45$2.00
Long-context rateSame rateOver 272K: $0.40 / $1.80Same rate
Price sourceMedian of 82 providersOfficial OpenAI APIOfficial Meta API
Limits
Context window1,000,000 tokens1,050,000 tokens (best)1,048,576 tokens
Max inputNot published922,000 tokensNot published
Max output384,000 tokens (best)128,000 tokens131,072 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesYes
AudioNoNoYes
VideoNoNoYes
ReasoningYesYeslow · medium · high · xhigh · maxYesminimal · low · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputNot publishedYesYes
File attachmentsYesYesYes
Temperature controlYesYesYes
Reasoning controlalwaysefforteffort
Availability
WeightsOpenMITProprietaryProprietary
API model IDNot publishedgpt-5.6-lunamuse-spark-1.3
API providers86 (best)5718
ReleasedSep 10, 2026Jul 9, 2026Sep 2, 2026
Knowledge cutoffMay 2025Feb 16, 2026Not published
Publisher documentationModel weightsPublisher documentationPublisher documentation
Source metadata updatedSep 10, 2026Jul 9, 2026Sep 2, 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.

  • DeepSeek V4.1 Flash$4.29
  • GPT-5.6 Luna$4.40
  • Muse Spark 1.3$21.00
04 — Questions

Which should you choose?

Which is better: DeepSeek V4.1 Flash, GPT-5.6 Luna or Muse Spark 1.3?

It is close. Our weighted score puts them within a point (DeepSeek V4.1 Flash 76/100, GPT-5.6 Luna 76/100, Muse Spark 1.3 68/100), so choose by what matters most for your work: Muse Spark 1.3 for raw capability and DeepSeek V4.1 Flash on price. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within 1 points (Muse Spark 1.3 82/100, DeepSeek V4.1 Flash 81/100, GPT-5.6 Luna 81/100), so choose by what matters most for your work: Muse Spark 1.3 for raw capability and DeepSeek V4.1 Flash on price. The score weighs capability 83%, context window 17%.

Which is cheaper, DeepSeek V4.1 Flash, GPT-5.6 Luna or Muse Spark 1.3?

DeepSeek V4.1 Flash is cheaper at $0.222 input / $1.04 output per million tokens (median across 82 API providers). GPT-5.6 Luna costs $0.20 input / $1.20 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). At a typical mix of three input tokens to one output token, that is $0.426 per million tokens for DeepSeek V4.1 Flash versus $0.45 for GPT-5.6 Luna (1.1× as much) and $2.00 for Muse Spark 1.3 (4.7× 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), DeepSeek V4.1 Flash 157.0 (#35 of 159) and GPT-5.6 Luna 156.7 (#37 of 159). The confidence ranges of the top two overlap (156.2–160.5 vs 155.1–159.2), so treat the gap as small. On individual benchmarks: FrontierMath Tiers 1–3 — GPT-5.6 Luna 82.1%, Muse Spark 1.3 74.4%, DeepSeek V4.1 Flash 67.4%; OTIS Mock AIME 2024–2025 — Muse Spark 1.3 99.2%, DeepSeek V4.1 Flash 98.3%, GPT-5.6 Luna 98.3%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek V4.1 Flash, GPT-5.6 Luna and Muse Spark 1.3 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-5.6 Luna and Muse Spark 1.3 have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for DeepSeek V4.1 Flash. Maximum output per response: DeepSeek V4.1 Flash up to 384,000, GPT-5.6 Luna up to 128,000, Muse Spark 1.3 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

DeepSeek V4.1 Flash accepts text and images; GPT-5.6 Luna accepts text, images and PDFs; Muse Spark 1.3 accepts text, images, PDFs, audio and video. Muse Spark 1.3 handles the widest range of inputs.

Are any of these open source?

DeepSeek V4.1 Flash publishes its weights (MIT) and can be self-hosted; GPT-5.6 Luna and Muse Spark 1.3 is proprietary.

Which is newer?

DeepSeek V4.1 Flash is the newest, released Sep 10, 2026. Muse Spark 1.3 came out Sep 2, 2026; GPT-5.6 Luna came out Jul 9, 2026. Knowledge cutoff: DeepSeek V4.1 Flash May 2025, GPT-5.6 Luna Feb 16, 2026.

How do you decide the winner?

This rating uses capability (59%, independent benchmark results); price (29%, blended price per million tokens (3 input : 1 output), log scale); context window (12%, 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 (83%, independent benchmark results); context window (17%, 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.