ZMIME
Comparison · 3 models · Updated Nov 22, 2026

Gemini 3.8 Flash vs DeepSeek V4 Pro 0813 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. Google

    Gemini 3.8 Flash

    Released Sep 2, 2026Latest

    74/100
    • ECI158.8
    • Price$0.75 / $3.75
    • Context1.05M
  2. DeepSeek

    DeepSeek V4 Pro 0813

    Released Aug 13, 2026

    67/100
    • ECI156.0
    • Price$0.66 / $1.98
    • Context1M
  3. Meta

    Muse Spark 1.3

    Released Sep 2, 2026Latest

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

    Gemini 3.8 Flash

    Released Sep 2, 2026Latest

    86/100
    • ECI158.8
    • Price$0.75 / $3.75
    • Context1.05M
  5. DeepSeek

    DeepSeek V4 Pro 0813

    Released Aug 13, 2026

    73/100
    • ECI156.0
    • Price$0.66 / $1.98
    • Context1M
  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 1.3Gemini 3.8 Flash: Text, Images, PDFs, Audio, Video · DeepSeek V4 Pro 0813: Text · Muse Spark 1.3: Text, Images, PDFs, Audio, Video
  • Self-hostingDeepSeek V4 Pro 0813Publishes downloadable weights (MIT)
How the score is built
MeasureWeightGemini 3.8 FlashDeepSeek V4 Pro 0813Muse Spark 1.3
CapabilityCapabilities Index (ECI)50%868386
Price25%404834
Inputs & features15%10045100
Context window10%656465
Overall100%74/10067/10073/100
How the score is built
MeasureWeightGemini 3.8 FlashDeepSeek V4 Pro 0813Muse Spark 1.3
CapabilityCapabilities Index (ECI)67%868386
Inputs & features20%10045100
Context window13%656465
Overall100%86/10073/10086/100
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.

Gemini 3.8 Flash vs DeepSeek V4 Pro 0813 vs Muse Spark 1.3 specifications side by side
SpecificationGemini 3.8 FlashGoogleDeepSeek V4 Pro 0813DeepSeekMuse Spark 1.3Meta
Capability
Capabilities Index (ECI)158.8 (best)156.0158.2
ECI rank#25 of 159 (best)#43 of 159#28 of 159
ECI confidence interval156.8–161.0154.1–158.1156.2–160.5
ECI evaluation dateSep 2, 2026Aug 13, 2026Sep 2, 2026
Documented capabilitiesGoogle's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflowsDeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modesMuse 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 questions95.4%high (best)91.7%maxNot published
FrontierMath Tiers 1–3Research-level mathematics68.4%high64.6%max74.4%xhigh (best)
OTIS Mock AIME 2024–2025Competition mathematics98.9%high98.6%max99.2%xhigh (best)
SimpleQA VerifiedShort factual questions69.7%high (best)52.9%maxNot published
Publisher-reported benchmarks
DeepSWE 1.1high thinking73.7pass@1Reported resultNot publishedNot published
GDPval-AA 2Publisher-reported result1545EloReported resultNot publishedNot published
Finance Agent 2Publisher-reported result61.4pass@1Reported resultNot publishedNot published
Harvey Legal Agent BenchmarkPublisher-reported result10all-pass rateReported resultNot publishedNot published
Terminal-Bench 2.1Publisher-reported result89.4pass@1Reported resultNot publishedNot published
Terminal-Bench 4.0Publisher-reported result19.1pass@1Reported resultNot publishedNot published
GDP.PDFPublisher-reported result35all-pass rateReported resultNot publishedNot published
CharXiv Reasoningwithout tools86.2pass@1Reported resultNot publishedNot published
LVBenchagentic87.8pass@1Reported resultNot publishedNot published
LVBenchstatic; 1024 frames; without tools87.1pass@1Reported resultNot publishedNot published
HLE-Verified · 1811 verified and revised itemsPublisher-reported result54.9accuracyReported resultNot publishedNot published
OSWorld 2.0 · before 2026-08-08 patchbatched tool calls; best of 3 runs; 500 steps59partial scoreReported resultNot publishedNot published
BioMysteryBench · human-solvablewith tools88.8pass@1Reported resultNot publishedNot published
BioMysteryBench · human-difficultwith tools56.5pass@1Reported resultNot publishedNot published
LAB-Bench 2 · 11 subtaskswith tools86.2macro-averageReported resultNot publishedNot published
Humanity's Last Examwithout toolsNot published42.7scoreReported resultNot published
Humanity's Last Examwith toolsNot published60scoreReported resultNot published
Terminal-Bench 2.1max effortNot published87.9scoreReported resultNot published
NL2Repomax effortNot published61.5scoreReported resultNot published
CyberGymmax effortNot published83.3scoreReported resultNot published
DeepSWEmax effortNot published62.7scoreReported resultNot published
Toolathlon-VerifiedPublisher-reported resultNot published74.1scoreReported resultNot published
Agents' Last ExamPublisher-reported resultNot published25.7scoreReported resultNot published
AutomationBench · publicPublisher-reported resultNot published31.8scoreReported resultNot published
DSBench-FullStack · internalPublisher-reported resultNot published71.1scoreReported resultNot published
DSBench-Hard · internalPublisher-reported resultNot published67.2scoreReported 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$0.75$0.66 (best)$1.25
Output$3.75$1.98 (best)$4.25
Cached input$0.075$0.022 (best)$0.15
Blended (3:1)$1.50$0.99 (best)$2.00
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Google APIOfficial DeepSeek APIOfficial Meta API
Limits
Context window1,048,576 tokens (best)1,000,000 tokens1,048,576 tokens (best)
Max inputNot publishedNot publishedNot published
Max output65,536 tokens384,000 tokens (best)131,072 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsYesNoYes
AudioYesNoYes
VideoYesNoYes
ReasoningYeslow · medium · highYeslow · high · maxYesminimal · low · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputYesYesYes
File attachmentsYesNoYes
Temperature controlYesYesYes
Reasoning controleffortefforteffort
Availability
WeightsProprietaryOpenMITProprietary
API model IDgemini-3.8-flashdeepseek-v4-promuse-spark-1.3
API providers4254 (best)18
ReleasedSep 2, 2026Aug 13, 2026Sep 2, 2026
Knowledge cutoffNot publishedNot publishedNot published
Publisher documentationPublisher documentationPublisher documentation · Model weightsPublisher documentation
Source metadata updatedSep 2, 2026Aug 22, 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.

  • Gemini 3.8 Flash$15.00
  • DeepSeek V4 Pro 0813$10.56
  • Muse Spark 1.3$21.00
04 — Questions

Which should you choose?

Which is better: Gemini 3.8 Flash, DeepSeek V4 Pro 0813 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, Gemini 3.8 Flash, DeepSeek V4 Pro 0813 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 Gemini 3.8 Flash, DeepSeek V4 Pro 0813 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: Gemini 3.8 Flash up to 65,536, DeepSeek V4 Pro 0813 up to 384,000, Muse Spark 1.3 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Gemini 3.8 Flash accepts text, images, PDFs, audio and video; DeepSeek V4 Pro 0813 accepts text; 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.