ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek V4 Pro vs Gemini 3.6 Flash vs GLM-5.1

Gemini 3.6 Flash comes out ahead, 83 to 67 and 66 on our weighted score, and it is the cheaper option too.

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek V4 Pro

    Released Apr 24, 2026

    67/100
    • ECI150.2
    • Price$1.60 / $3.33
    • Context1M
  2. Our pick

    Google

    Gemini 3.6 Flash

    Released Jul 21, 2026

    83/100
    • ECI155.2
    • Price$0.75 / $3.75
    • Context1.05M
  3. Z.ai (Zhipu)

    GLM-5.1

    Released Apr 7, 2026

    66/100
    • ECI150.7
    • Price$1.40 / $4.40
    • Context200K
01 — Verdict

Gemini 3.6 Flash is our pick

Gemini 3.6 Flash is the better all-round choice, scoring 83/100 against DeepSeek V4 Pro (67) and GLM-5.1 (66). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityGemini 3.6 FlashCapabilities Index (ECI): Gemini 3.6 Flash 155.2 · GLM-5.1 150.7 · DeepSeek V4 Pro 150.2
  • Lowest priceGemini 3.6 FlashGemini 3.6 Flash $1.50 · DeepSeek V4 Pro $2.03 · GLM-5.1 $2.15 per 1M tokens (3:1 blend)
  • Longest contextGemini 3.6 FlashGemini 3.6 Flash 1,048,576 · DeepSeek V4 Pro 1,000,000 · GLM-5.1 200,000 tokens
  • Widest inputsGemini 3.6 FlashDeepSeek V4 Pro: Text · Gemini 3.6 Flash: Text, Images, PDFs, Audio, Video · GLM-5.1: Text
  • Self-hostingDeepSeek V4 Pro and GLM-5.1Publishes downloadable weights
How the score is built
MeasureWeightDeepSeek V4 ProGemini 3.6 FlashGLM-5.1
CapabilityCapabilities Index (ECI)67%778278
Inputs & features20%3510045
Context window13%646539
Overall100%67/10083/10066/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

DeepSeek V4 Pro vs Gemini 3.6 Flash vs GLM-5.1 specifications side by side
SpecificationDeepSeek V4 ProDeepSeekGemini 3.6 FlashGoogleGLM-5.1Z.ai (Zhipu)
Capability
Capabilities Index (ECI)150.2155.2 (best)150.7
ECI rank#67 of 158#45 of 158 (best)#66 of 158
GPQA DiamondGraduate-level science questions90.9%94.1% (best)89.9%
FrontierMath Tiers 1–3Research-level mathematics45.3%59.0% (best)36.8%
OTIS Mock AIME 2024–2025Competition mathematics96.7% (best)94.2%93.3%
SWE-bench VerifiedFixing real GitHub issues77.6% (best)—74.2%
SimpleQA VerifiedShort factual questions47.0%66.2% (best)34.0%
Price per million tokens
Input$1.60$0.75 (best)$1.40
Output$3.33 (best)$3.75$4.40
Cached input—$0.075 (best)$0.26
Blended (3:1)$2.03$1.50 (best)$2.15
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 65 providersOfficial Google APIOfficial Z.AI API
Limits
Context window1,000,000 tokens1,048,576 tokens (best)200,000 tokens
Max output384,000 tokens (best)65,536 tokens131,072 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoYesNo
VideoNoYesNo
ReasoningYesYesminimal · low · medium · highYes
Tool callingYesYesYes
Structured outputNoYesYes
Availability
WeightsOpenProprietaryOpen
API model ID—gemini-3.6-flashglm-5.1
API providers67 (best)3146
ReleasedApr 24, 2026Jul 21, 2026Apr 7, 2026
Knowledge cutoffMay 2025Mar 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$22.66
  • Gemini 3.6 Flash$15.00
  • GLM-5.1$22.80
04 — Questions

Which should you choose?

Which is better: DeepSeek V4 Pro, Gemini 3.6 Flash or GLM-5.1?

Gemini 3.6 Flash is the better all-round choice, scoring 83/100 against DeepSeek V4 Pro (67) and GLM-5.1 (66). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, DeepSeek V4 Pro, Gemini 3.6 Flash or GLM-5.1?

Gemini 3.6 Flash is cheaper at $0.75 input / $3.75 output per million tokens (official Google API price). DeepSeek V4 Pro costs $1.60 input / $3.33 output per million tokens (median across 65 API providers); GLM-5.1 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 $1.50 per million tokens for Gemini 3.6 Flash versus $2.03 for DeepSeek V4 Pro (1.4× as much) and $2.15 for GLM-5.1 (1.4× as much).

Which scores higher on benchmarks?

Gemini 3.6 Flash scores higher on the Capabilities Index (ECI): Gemini 3.6 Flash 155.2 (#45 of 158), GLM-5.1 150.7 (#66 of 158) and DeepSeek V4 Pro 150.2 (#67 of 158). Their confidence ranges do not overlap (153.4–157.2 vs 148.8–152.8), so the gap is a real one. On individual benchmarks: GPQA Diamond — Gemini 3.6 Flash 94.1%, DeepSeek V4 Pro 90.9%, GLM-5.1 89.9%; FrontierMath Tiers 1–3 — Gemini 3.6 Flash 59.0%, DeepSeek V4 Pro 45.3%, GLM-5.1 36.8%; OTIS Mock AIME 2024–2025 — DeepSeek V4 Pro 96.7%, Gemini 3.6 Flash 94.2%, GLM-5.1 93.3%; SimpleQA Verified — Gemini 3.6 Flash 66.2%, DeepSeek V4 Pro 47.0%, GLM-5.1 34.0%.

Which is better for coding?

There are no published SWE-bench Verified results for Gemini 3.6 Flash yet, so there is no like-for-like coding score. On overall capability, Gemini 3.6 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 3.6 Flash has the largest context window at 1,048,576 tokens, against 1,000,000 for DeepSeek V4 Pro and 200,000 for GLM-5.1. Maximum output per response: DeepSeek V4 Pro up to 384,000, Gemini 3.6 Flash up to 65,536, GLM-5.1 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

DeepSeek V4 Pro accepts text; Gemini 3.6 Flash accepts text, images, PDFs, audio and video; GLM-5.1 accepts text. Gemini 3.6 Flash handles the widest range of inputs.

Are any of these open source?

DeepSeek V4 Pro and GLM-5.1 publishes its weights and can be self-hosted; Gemini 3.6 Flash is proprietary.

Which is newer?

Gemini 3.6 Flash is the newest, released Jul 21, 2026. DeepSeek V4 Pro came out Apr 24, 2026; GLM-5.1 came out Apr 7, 2026. Knowledge cutoff: DeepSeek V4 Pro May 2025, Gemini 3.6 Flash Mar 2026.

How do you decide the winner?

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 18, 2026.