ZMIME
Comparison · 2 models · Updated Nov 22, 2026

DeepSeek V4 Pro 0813 vs Gemini 3.8 Flash

Gemini 3.8 Flash comes out ahead, 74 to 67 on our weighted score, though DeepSeek V4 Pro 0813 is 34% cheaper per token.Gemini 3.8 Flash comes out ahead, 86 to 73 on our weighted score, though DeepSeek V4 Pro 0813 is 34% cheaper per token.

  1. DeepSeek

    DeepSeek V4 Pro 0813

    Released Aug 13, 2026

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

    Google

    Gemini 3.8 Flash

    Released Sep 2, 2026Latest

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

    DeepSeek V4 Pro 0813

    Released Aug 13, 2026

    73/100
    • ECI156.0
    • Price$0.66 / $1.98
    • Context1M
  4. Our pick

    Google

    Gemini 3.8 Flash

    Released Sep 2, 2026Latest

    86/100
    • ECI158.8
    • Price$0.75 / $3.75
    • Context1.05M
  5. Add a model

    Make it a three-way comparison.

01 — Verdict

Gemini 3.8 Flash is our pick

Gemini 3.8 Flash is the better all-round choice, scoring 74/100 against DeepSeek V4 Pro 0813 (67). It leads on capability and inputs & features. DeepSeek V4 Pro 0813 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Gemini 3.8 Flash is the better all-round choice, scoring 86/100 against DeepSeek V4 Pro 0813 (73). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityGemini 3.8 FlashCapabilities Index (ECI): Gemini 3.8 Flash 158.8 · DeepSeek V4 Pro 0813 156.0
  • Lowest priceDeepSeek V4 Pro 0813DeepSeek V4 Pro 0813 $0.99 · Gemini 3.8 Flash $1.50 per 1M tokens (3:1 blend)
  • Longest contextGemini 3.8 FlashGemini 3.8 Flash 1,048,576 · DeepSeek V4 Pro 0813 1,000,000 tokens
  • Widest inputsGemini 3.8 FlashDeepSeek V4 Pro 0813: Text · Gemini 3.8 Flash: Text, Images, PDFs, Audio, Video
  • Self-hostingDeepSeek V4 Pro 0813Publishes downloadable weights (MIT)
How the score is built
MeasureWeightDeepSeek V4 Pro 0813Gemini 3.8 Flash
CapabilityCapabilities Index (ECI)50%8386
Price25%4840
Inputs & features15%45100
Context window10%6465
Overall100%67/10074/100
How the score is built
MeasureWeightDeepSeek V4 Pro 0813Gemini 3.8 Flash
CapabilityCapabilities Index (ECI)67%8386
Inputs & features20%45100
Context window13%6465
Overall100%73/10086/100
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 specifications side by side
SpecificationDeepSeek V4 Pro 0813DeepSeekGemini 3.8 FlashGoogle
Capability
Capabilities Index (ECI)156.0158.8 (best)
ECI rank#43 of 159#25 of 159 (best)
ECI confidence interval154.1–158.1156.8–161.0
ECI evaluation dateAug 13, 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 workflows
Model parametersNot publishedNot published
Output modalitiesTextText
GPQA DiamondGraduate-level science questions91.7%max95.4%high (best)
FrontierMath Tiers 1–3Research-level mathematics64.6%max68.4%high (best)
OTIS Mock AIME 2024–2025Competition mathematics98.6%max98.9%high (best)
SimpleQA VerifiedShort factual questions52.9%max69.7%high (best)
Publisher-reported benchmarks
Humanity's Last Examwithout tools42.7scoreReported resultNot published
Humanity's Last Examwith tools60scoreReported resultNot published
Terminal-Bench 2.1max effort87.9scoreReported resultNot published
NL2Repomax effort61.5scoreReported resultNot published
CyberGymmax effort83.3scoreReported resultNot published
DeepSWEmax effort62.7scoreReported resultNot published
Toolathlon-VerifiedPublisher-reported result74.1scoreReported resultNot published
Agents' Last ExamPublisher-reported result25.7scoreReported resultNot published
AutomationBench · publicPublisher-reported result31.8scoreReported resultNot published
DSBench-FullStack · internalPublisher-reported result71.1scoreReported resultNot published
DSBench-Hard · internalPublisher-reported result67.2scoreReported resultNot published
DeepSWE 1.1high thinkingNot published73.7pass@1Reported result
GDPval-AA 2Publisher-reported resultNot published1545EloReported result
Finance Agent 2Publisher-reported resultNot published61.4pass@1Reported result
Harvey Legal Agent BenchmarkPublisher-reported resultNot published10all-pass rateReported result
Terminal-Bench 2.1Publisher-reported resultNot published89.4pass@1Reported result
Terminal-Bench 4.0Publisher-reported resultNot published19.1pass@1Reported result
GDP.PDFPublisher-reported resultNot published35all-pass rateReported result
CharXiv Reasoningwithout toolsNot published86.2pass@1Reported result
LVBenchagenticNot published87.8pass@1Reported result
LVBenchstatic; 1024 frames; without toolsNot published87.1pass@1Reported result
HLE-Verified · 1811 verified and revised itemsPublisher-reported resultNot published54.9accuracyReported result
OSWorld 2.0 · before 2026-08-08 patchbatched tool calls; best of 3 runs; 500 stepsNot published59partial scoreReported result
BioMysteryBench · human-solvablewith toolsNot published88.8pass@1Reported result
BioMysteryBench · human-difficultwith toolsNot published56.5pass@1Reported result
LAB-Bench 2 · 11 subtaskswith toolsNot published86.2macro-averageReported result
Price per million tokens
Input$0.66 (best)$0.75
Output$1.98 (best)$3.75
Cached input$0.022 (best)$0.075
Blended (3:1)$0.99 (best)$1.50
Long-context rateSame rateSame rate
Price sourceOfficial DeepSeek APIOfficial Google API
Limits
Context window1,000,000 tokens1,048,576 tokens (best)
Max inputNot publishedNot published
Max output384,000 tokens (best)65,536 tokens
Inputs and features
TextYesYes
ImagesNoYes
PDFsNoYes
AudioNoYes
VideoNoYes
ReasoningYeslow · high · maxYeslow · medium · high
Tool callingYesYes
Structured outputYesYes
File attachmentsNoYes
Temperature controlYesYes
Reasoning controlefforteffort
Availability
WeightsOpenMITProprietary
API model IDdeepseek-v4-progemini-3.8-flash
API providers54 (best)42
ReleasedAug 13, 2026Sep 2, 2026
Knowledge cutoffNot publishedNot published
Publisher documentationPublisher documentation · Model weightsPublisher documentation
Source metadata updatedAug 22, 2026Sep 2, 2026
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 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
04 — Questions

Which should you choose?

Which is better: DeepSeek V4 Pro 0813 or Gemini 3.8 Flash?

Gemini 3.8 Flash is the better all-round choice, scoring 74/100 against DeepSeek V4 Pro 0813 (67). It leads on capability and inputs & features. DeepSeek V4 Pro 0813 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Gemini 3.8 Flash is the better all-round choice, scoring 86/100 against DeepSeek V4 Pro 0813 (73). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

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

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). 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).

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) and DeepSeek V4 Pro 0813 156.0 (#43 of 159). The confidence ranges of the top two overlap (156.8–161.0 vs 154.1–158.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 3.8 Flash 95.4%, DeepSeek V4 Pro 0813 91.7%; FrontierMath Tiers 1–3 — Gemini 3.8 Flash 68.4%, DeepSeek V4 Pro 0813 64.6%; OTIS Mock AIME 2024–2025 — Gemini 3.8 Flash 98.9%, DeepSeek V4 Pro 0813 98.6%; SimpleQA Verified — Gemini 3.8 Flash 69.7%, DeepSeek V4 Pro 0813 52.9%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek V4 Pro 0813 and Gemini 3.8 Flash 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. Both support tool calling for agent workflows.

Which has the bigger context window?

Gemini 3.8 Flash has the largest context window at 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 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. 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 is proprietary.

Which is newer?

Gemini 3.8 Flash is the newest, released 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.