ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek-V3 vs Magistral Small vs Magistral Small 1.2

Too close to call on our weighted score (Magistral Small 1.2 42, Magistral Small 40, DeepSeek-V3 33). The right pick depends on what you value most.

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek-V3

    Released Dec 26, 2024

    33/100
    • ECI131.7
    • Price$0.32 / $1.10
    • Context131K
  2. Mistral AI

    Magistral Small

    Released Jun 10, 2025

    40/100
    • ECI—
    • Price$0.50 / $1.50
    • Context131K
  3. Mistral AI

    Magistral Small 1.2

    Released Sep 18, 2025

    42/100
    • ECI—
    • Price$0.50 / $1.50
    • Context131K
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 2 points (Magistral Small 1.2 42/100, Magistral Small 40/100, DeepSeek-V3 33/100), so choose by what matters most for your work: Magistral Small for raw capability and DeepSeek-V3 on price. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Magistral Small and Magistral Small 1.2 has no Capabilities Index score yet.

  • CapabilityMagistral SmallShared benchmarks: Magistral Small 43.0% · Magistral Small 1.2 37.8% · DeepSeek-V3 36.2%
  • Lowest priceDeepSeek-V3DeepSeek-V3 $0.515 · Magistral Small $0.75 · Magistral Small 1.2 $0.75 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameDeepSeek-V3 131,072 · Magistral Small 131,072 · Magistral Small 1.2 131,072 tokens
  • Widest inputsMagistral Small 1.2DeepSeek-V3: Text · Magistral Small: Text · Magistral Small 1.2: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightDeepSeek-V3Magistral SmallMagistral Small 1.2
CapabilityShared benchmarks67%364338
Inputs & features20%253560
Context window13%323232
Overall100%33/10040/10042/100
02 — Side by side

Every spec in one table

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

DeepSeek-V3 vs Magistral Small vs Magistral Small 1.2 specifications side by side
SpecificationDeepSeek-V3DeepSeekMagistral SmallMistral AIMagistral Small 1.2Mistral AI
Capability
Capabilities Index (ECI)131.7——
ECI rank#136 of 158——
GPQA DiamondGraduate-level science questions56.5% (best)56.1%47.6%
OTIS Mock AIME 2024–2025Competition mathematics15.8%30.0% (best)28.1%
Price per million tokens
Input$0.32 (best)$0.50$0.50
Output$1.10 (best)$1.50$1.50
Cached input———
Blended (3:1)$0.515 (best)$0.75$0.75
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 9 providersMedian of 1 providersMedian of 1 providers
Limits
Context window131,072 tokens131,072 tokens131,072 tokens
Max output8,192 tokens8,192 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoYesYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenDeepSeek Model LicenseOpenApache 2.0OpenApache 2.0
API model ID———
API providers9 (best)21
ReleasedDec 26, 2024Jun 10, 2025Sep 18, 2025
Knowledge cutoff———
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$5.40
  • Magistral Small$8.00
  • Magistral Small 1.2$8.00
04 — Questions

Which should you choose?

Which is better: DeepSeek-V3, Magistral Small or Magistral Small 1.2?

It is close. Our weighted score puts them within 2 points (Magistral Small 1.2 42/100, Magistral Small 40/100, DeepSeek-V3 33/100), so choose by what matters most for your work: Magistral Small for raw capability and DeepSeek-V3 on price. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Magistral Small and Magistral Small 1.2 has no Capabilities Index score yet.

Which is cheaper, DeepSeek-V3, Magistral Small or Magistral Small 1.2?

DeepSeek-V3 is cheaper at $0.32 input / $1.10 output per million tokens (median across 9 API providers). Magistral Small costs $0.50 input / $1.50 output per million tokens (median across 1 API provider); Magistral Small 1.2 costs $0.50 input / $1.50 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.515 per million tokens for DeepSeek-V3 versus $0.75 for Magistral Small (1.5× as much) and $0.75 for Magistral Small 1.2 (1.5× as much).

Which scores higher on benchmarks?

Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): Magistral Small 43.0%, Magistral Small 1.2 37.8% and DeepSeek-V3 36.2%. On individual benchmarks: GPQA Diamond — DeepSeek-V3 56.5%, Magistral Small 56.1%, Magistral Small 1.2 47.6%; OTIS Mock AIME 2024–2025 — Magistral Small 30.0%, Magistral Small 1.2 28.1%, DeepSeek-V3 15.8%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek-V3, Magistral Small and Magistral Small 1.2 yet, so there is no like-for-like coding score. On overall capability, Magistral Small 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, Magistral Small and Magistral Small 1.2 share the same 131,072-token context window. Maximum output per response: DeepSeek-V3 up to 8,192, Magistral Small up to 8,192, Magistral Small 1.2 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

DeepSeek-V3 accepts text; Magistral Small accepts text; Magistral Small 1.2 accepts text and images. Magistral Small 1.2 handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (DeepSeek Model License and Apache 2.0), so you can self-host them.

Which is newer?

Magistral Small 1.2 is the newest, released Sep 18, 2025. Magistral Small came out Jun 10, 2025; DeepSeek-V3 came out Dec 26, 2024.

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.