ZMIME
Comparison · 3 models · Updated Nov 22, 2026

DeepSeek V4 Pro 0813 vs Gemini 3.8 Flash vs Muse Spark 1.3

Too close to call on our weighted score (Gemini 3.8 Flash 74, Muse Spark 1.3 73, DeepSeek V4 Pro 0813 67). The right pick depends on what you value most.Too close to call on our weighted score (Gemini 3.8 Flash 86, Muse Spark 1.3 86, DeepSeek V4 Pro 0813 73). The right pick depends on what you value most.

  1. DeepSeek

    DeepSeek V4 Pro 0813

    Released Aug 13, 2026

    67/100
    • ECI156.0
    • Price$0.66 / $1.98
    • Context1M
  2. Google

    Gemini 3.8 Flash

    Released Sep 2, 2026Latest

    74/100
    • ECI158.8
    • Price$0.75 / $3.75
    • Context1.05M
  3. Meta

    Muse Spark 1.3

    Released Sep 2, 2026Latest

    73/100
    • ECI158.2
    • Price$1.25 / $4.25
    • Context1.05M
  4. DeepSeek

    DeepSeek V4 Pro 0813

    Released Aug 13, 2026

    73/100
    • ECI156.0
    • Price$0.66 / $1.98
    • Context1M
  5. Google

    Gemini 3.8 Flash

    Released Sep 2, 2026Latest

    86/100
    • ECI158.8
    • Price$0.75 / $3.75
    • Context1.05M
  6. Meta

    Muse Spark 1.3

    Released Sep 2, 2026Latest

    86/100
    • ECI158.2
    • Price$1.25 / $4.25
    • Context1.05M
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 2 points (Gemini 3.8 Flash 74/100, Muse Spark 1.3 73/100, DeepSeek V4 Pro 0813 67/100), so choose by what matters most for your work: Gemini 3.8 Flash for raw capability and DeepSeek V4 Pro 0813 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.It is close. Our weighted score puts them within a point (Gemini 3.8 Flash 86/100, Muse Spark 1.3 86/100, DeepSeek V4 Pro 0813 73/100), so choose by what matters most for your work: Gemini 3.8 Flash for raw capability and DeepSeek V4 Pro 0813 on price. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityGemini 3.8 FlashCapabilities Index (ECI): Gemini 3.8 Flash 158.8 · Muse Spark 1.3 158.2 · DeepSeek V4 Pro 0813 156.0
  • Lowest priceDeepSeek V4 Pro 0813DeepSeek V4 Pro 0813 $0.99 · Gemini 3.8 Flash $1.50 · Muse Spark 1.3 $2.00 per 1M tokens (3:1 blend)
  • Longest contextGemini 3.8 Flash and Muse Spark 1.3Gemini 3.8 Flash 1,048,576 · Muse Spark 1.3 1,048,576 · DeepSeek V4 Pro 0813 1,000,000 tokens
  • Widest inputsGemini 3.8 Flash and Muse Spark 1.3DeepSeek V4 Pro 0813: Text · Gemini 3.8 Flash: Text, Images, PDFs, Audio, Video · Muse Spark 1.3: Text, Images, PDFs, Audio, Video
  • Self-hostingDeepSeek V4 Pro 0813Publishes downloadable weights (MIT)
How the score is built
MeasureWeightDeepSeek V4 Pro 0813Gemini 3.8 FlashMuse Spark 1.3
CapabilityCapabilities Index (ECI)50%838686
Price25%484034
Inputs & features15%45100100
Context window10%646565
Overall100%67/10074/10073/100
How the score is built
MeasureWeightDeepSeek V4 Pro 0813Gemini 3.8 FlashMuse Spark 1.3
CapabilityCapabilities Index (ECI)67%838686
Inputs & features20%45100100
Context window13%646565
Overall100%73/10086/10086/100
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.

DeepSeek V4 Pro 0813 vs Gemini 3.8 Flash vs Muse Spark 1.3 specifications side by side
SpecificationDeepSeek V4 Pro 0813DeepSeekGemini 3.8 FlashGoogleMuse Spark 1.3Meta
Capability
Capabilities Index (ECI)156.0158.8 (best)158.2
ECI rank#43 of 159#25 of 159 (best)#28 of 159
ECI confidence interval154.1–158.1156.8–161.0156.2–160.5
ECI evaluation dateAug 13, 2026Sep 2, 2026Sep 2, 2026
Documented capabilitiesDeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modesGoogle's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflowsMuse 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 questions91.7%max95.4%high (best)Not published
FrontierMath Tiers 1–3Research-level mathematics64.6%max68.4%high74.4%xhigh (best)
OTIS Mock AIME 2024–2025Competition mathematics98.6%max98.9%high99.2%xhigh (best)
SimpleQA VerifiedShort factual questions52.9%max69.7%high (best)Not published
Publisher-reported benchmarks
Humanity's Last Examwithout tools42.7scoreReported resultNot publishedNot published
Humanity's Last Examwith tools60scoreReported resultNot publishedNot published
Terminal-Bench 2.1max effort87.9scoreReported resultNot publishedNot published
NL2Repomax effort61.5scoreReported resultNot publishedNot published
CyberGymmax effort83.3scoreReported resultNot publishedNot published
DeepSWEmax effort62.7scoreReported resultNot publishedNot published
Toolathlon-VerifiedPublisher-reported result74.1scoreReported resultNot publishedNot published
Agents' Last ExamPublisher-reported result25.7scoreReported resultNot publishedNot published
AutomationBench · publicPublisher-reported result31.8scoreReported resultNot publishedNot published
DSBench-FullStack · internalPublisher-reported result71.1scoreReported resultNot publishedNot published
DSBench-Hard · internalPublisher-reported result67.2scoreReported resultNot publishedNot published
DeepSWE 1.1high thinkingNot published73.7pass@1Reported resultNot published
GDPval-AA 2Publisher-reported resultNot published1545EloReported resultNot published
Finance Agent 2Publisher-reported resultNot published61.4pass@1Reported resultNot published
Harvey Legal Agent BenchmarkPublisher-reported resultNot published10all-pass rateReported resultNot published
Terminal-Bench 2.1Publisher-reported resultNot published89.4pass@1Reported resultNot published
Terminal-Bench 4.0Publisher-reported resultNot published19.1pass@1Reported resultNot published
GDP.PDFPublisher-reported resultNot published35all-pass rateReported resultNot published
CharXiv Reasoningwithout toolsNot published86.2pass@1Reported resultNot published
LVBenchagenticNot published87.8pass@1Reported resultNot published
LVBenchstatic; 1024 frames; without toolsNot published87.1pass@1Reported resultNot published
HLE-Verified · 1811 verified and revised itemsPublisher-reported resultNot published54.9accuracyReported resultNot published
OSWorld 2.0 · before 2026-08-08 patchbatched tool calls; best of 3 runs; 500 stepsNot published59partial scoreReported resultNot published
BioMysteryBench · human-solvablewith toolsNot published88.8pass@1Reported resultNot published
BioMysteryBench · human-difficultwith toolsNot published56.5pass@1Reported resultNot published
LAB-Bench 2 · 11 subtaskswith toolsNot published86.2macro-averageReported resultNot 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$0.66 (best)$0.75$1.25
Output$1.98 (best)$3.75$4.25
Cached input$0.022 (best)$0.075$0.15
Blended (3:1)$0.99 (best)$1.50$2.00
Long-context rateSame rateSame rateSame rate
Price sourceOfficial DeepSeek APIOfficial Google APIOfficial Meta API
Limits
Context window1,000,000 tokens1,048,576 tokens (best)1,048,576 tokens (best)
Max inputNot publishedNot publishedNot published
Max output384,000 tokens (best)65,536 tokens131,072 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoYesYes
AudioNoYesYes
VideoNoYesYes
ReasoningYeslow · high · maxYeslow · medium · highYesminimal · low · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputYesYesYes
File attachmentsNoYesYes
Temperature controlYesYesYes
Reasoning controleffortefforteffort
Availability
WeightsOpenMITProprietaryProprietary
API model IDdeepseek-v4-progemini-3.8-flashmuse-spark-1.3
API providers54 (best)4218
ReleasedAug 13, 2026Sep 2, 2026Sep 2, 2026
Knowledge cutoffNot publishedNot publishedNot published
Publisher documentationPublisher documentation · Model weightsPublisher documentationPublisher documentation
Source metadata updatedAug 22, 2026Sep 2, 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 Pro 0813$10.56
  • Gemini 3.8 Flash$15.00
  • Muse Spark 1.3$21.00
04 — Questions

Which should you choose?

Which is better: DeepSeek V4 Pro 0813, Gemini 3.8 Flash or Muse Spark 1.3?

It is close. Our weighted score puts them within 2 points (Gemini 3.8 Flash 74/100, Muse Spark 1.3 73/100, DeepSeek V4 Pro 0813 67/100), so choose by what matters most for your work: Gemini 3.8 Flash for raw capability and DeepSeek V4 Pro 0813 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.It is close. Our weighted score puts them within a point (Gemini 3.8 Flash 86/100, Muse Spark 1.3 86/100, DeepSeek V4 Pro 0813 73/100), so choose by what matters most for your work: Gemini 3.8 Flash for raw capability and DeepSeek V4 Pro 0813 on price. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, DeepSeek V4 Pro 0813, Gemini 3.8 Flash or Muse Spark 1.3?

DeepSeek V4 Pro 0813 is cheaper at $0.66 input / $1.98 output per million tokens (official DeepSeek API price). Gemini 3.8 Flash costs $0.75 input / $3.75 output per million tokens (official Google 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 $0.99 per million tokens for DeepSeek V4 Pro 0813 versus $1.50 for Gemini 3.8 Flash (1.5× as much) and $2.00 for Muse Spark 1.3 (2× as much).

Which scores higher on benchmarks?

Gemini 3.8 Flash scores higher on the Capabilities Index (ECI): Gemini 3.8 Flash 158.8 (#25 of 159), Muse Spark 1.3 158.2 (#28 of 159) and DeepSeek V4 Pro 0813 156.0 (#43 of 159). The confidence ranges of the top two overlap (156.8–161.0 vs 156.2–160.5), so treat the gap as small. On individual benchmarks: FrontierMath Tiers 1–3 — Muse Spark 1.3 74.4%, Gemini 3.8 Flash 68.4%, DeepSeek V4 Pro 0813 64.6%; OTIS Mock AIME 2024–2025 — Muse Spark 1.3 99.2%, Gemini 3.8 Flash 98.9%, DeepSeek V4 Pro 0813 98.6%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek V4 Pro 0813, Gemini 3.8 Flash and Muse Spark 1.3 yet, so there is no like-for-like coding score. On overall capability, Gemini 3.8 Flash 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?

Gemini 3.8 Flash and Muse Spark 1.3 have the largest context windows (1,048,576 and 1,048,576 tokens), against 1,000,000 for DeepSeek V4 Pro 0813. Maximum output per response: DeepSeek V4 Pro 0813 up to 384,000, Gemini 3.8 Flash up to 65,536, Muse Spark 1.3 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

DeepSeek V4 Pro 0813 accepts text; Gemini 3.8 Flash accepts text, images, PDFs, audio and video; Muse Spark 1.3 accepts text, images, PDFs, audio and video. Gemini 3.8 Flash handles the widest range of inputs.

Are any of these open source?

DeepSeek V4 Pro 0813 publishes its weights (MIT) and can be self-hosted; Gemini 3.8 Flash and Muse Spark 1.3 is proprietary.

Which is newer?

Gemini 3.8 Flash is the newest, released Sep 2, 2026. Muse Spark 1.3 came out Sep 2, 2026; DeepSeek V4 Pro 0813 came out Aug 13, 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.