ZMIME
Comparison · 3 models · Updated Oct 4, 2026

DeepSeek-V3.1 vs Mistral Medium 3 vs Qwen3 14B

Too close to call on our weighted score (DeepSeek-V3.1 55, Qwen3 14B 54, Mistral Medium 3 53). The right pick depends on what you value most.

  1. DeepSeek

    DeepSeek-V3.1

    Released Aug 21, 2025

    55/100
    • ECI139.9
    • Price$0.385 / $1.25
    • Context131K
    Full specs Remove DeepSeek-V3.1

  2. Mistral AI

    Mistral Medium 3

    Released May 7, 2025

    53/100
    • ECI134.1
    • Price$0.40 / $2.00
    • Context131K
    Full specs Remove Mistral Medium 3

  3. Alibaba (Qwen)

    Qwen3 14B

    Released Apr 29, 2025

    54/100
    • ECI138.2
    • Price$0.35 / $1.40
    • Context131K
    Full specs Remove Qwen3 14B
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 1 points (DeepSeek-V3.1 55/100, Qwen3 14B 54/100, Mistral Medium 3 53/100), so choose by what matters most for your work: DeepSeek-V3.1 for raw capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityDeepSeek-V3.1Capabilities Index (ECI): DeepSeek-V3.1 139.9 · Qwen3 14B 138.2 · Mistral Medium 3 134.1
  • Lowest priceDeepSeek-V3.1DeepSeek-V3.1 $0.601 · Qwen3 14B $0.613 · Mistral Medium 3 $0.80 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameDeepSeek-V3.1 131,072 · Mistral Medium 3 131,072 · Qwen3 14B 131,072 tokens
  • Widest inputsMistral Medium 3DeepSeek-V3.1: Text · Mistral Medium 3: Text, Images · Qwen3 14B: Text
  • Self-hostingDeepSeek-V3.1 and Qwen3 14BPublishes downloadable weights (MIT License)
How the score is built
MeasureWeightDeepSeek-V3.1Mistral Medium 3Qwen3 14B
CapabilityCapabilities Index (ECI)50%655863
Price25%605460
Inputs & features15%355035
Context window10%242424
Overall100%55/10053/10054/100
02 — Side by side

Every spec in one table

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

DeepSeek-V3.1 vs Mistral Medium 3 vs Qwen3 14B specifications side by side
SpecificationDeepSeek-V3.1DeepSeekMistral Medium 3Mistral AIQwen3 14BAlibaba (Qwen)
Capability
Capabilities Index (ECI)139.9 (best)134.1138.2
ECI rank#100 of 148 (best)#117 of 148#107 of 148
GPQA DiamondGraduate-level science questions—59.5%63.8% (best)
OTIS Mock AIME 2024–2025Competition mathematics—32.2%66.4% (best)
Price per million tokens
Input$0.385$0.40$0.35 (best)
Output$1.25 (best)$2.00$1.40
Cached input———
Blended (3:1)$0.601 (best)$0.80$0.613
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 8 providersOfficial Mistral APIOfficial Alibaba API
Limits
Context window131,072 tokens131,072 tokens131,072 tokens
Max output8,192 tokens131,072 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenMIT LicenseProprietaryOpen
API model ID—mistral-medium-2505qwen3-14b
API providers8 (best)51
ReleasedAug 21, 2025May 7, 2025Apr 29, 2025
Knowledge cutoff—May 2025Apr 2025
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-V3.1$6.35
  • Mistral Medium 3$8.00
  • Qwen3 14B$6.30
04 — Questions

Which should you choose?

Which is better: DeepSeek-V3.1, Mistral Medium 3 or Qwen3 14B?

It is close. Our weighted score puts them within 1 points (DeepSeek-V3.1 55/100, Qwen3 14B 54/100, Mistral Medium 3 53/100), so choose by what matters most for your work: DeepSeek-V3.1 for raw capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, DeepSeek-V3.1, Mistral Medium 3 or Qwen3 14B?

DeepSeek-V3.1 is cheaper at $0.385 input / $1.25 output per million tokens (median across 8 API providers). Qwen3 14B costs $0.35 input / $1.40 output per million tokens (official Alibaba API price); Mistral Medium 3 costs $0.40 input / $2.00 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.601 per million tokens for DeepSeek-V3.1 versus $0.613 for Qwen3 14B (1× as much) and $0.80 for Mistral Medium 3 (1.3× as much).

Which scores higher on benchmarks?

DeepSeek-V3.1 scores higher on the Capabilities Index (ECI): DeepSeek-V3.1 139.9 (#100 of 148), Qwen3 14B 138.2 (#107 of 148) and Mistral Medium 3 134.1 (#117 of 148). The confidence ranges of the top two overlap (136.1–143.3 vs 133.5–140.1), so treat the gap as small.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek-V3.1, Mistral Medium 3 and Qwen3 14B yet, so there is no like-for-like coding score. On overall capability, DeepSeek-V3.1 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?

DeepSeek-V3.1, Mistral Medium 3 and Qwen3 14B share the same 131,072-token context window. Maximum output per response: DeepSeek-V3.1 up to 8,192, Mistral Medium 3 up to 131,072, Qwen3 14B up to 8,192 tokens.

Which can read images, PDFs, audio or video?

DeepSeek-V3.1 accepts text; Mistral Medium 3 accepts text and images; Qwen3 14B accepts text. Mistral Medium 3 handles the widest range of inputs.

Are any of these open source?

DeepSeek-V3.1 and Qwen3 14B publishes its weights (MIT License) and can be self-hosted; Mistral Medium 3 is proprietary.

Which is newer?

DeepSeek-V3.1 is the newest, released Aug 21, 2025. Mistral Medium 3 came out May 7, 2025; Qwen3 14B came out Apr 29, 2025. Knowledge cutoff: Mistral Medium 3 May 2025, Qwen3 14B Apr 2025.

How do you decide the winner?

Each model gets a 0–100 score on 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons