ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Ministral 3B vs Mixtral 8x7B vs Llama-3.1-8B-Instruct

Ministral 3B comes out ahead, 49 to 46 and 37 on our weighted score, and it is the cheaper option too.

  1. Our pick

    Mistral AI

    Ministral 3B

    Released Oct 16, 2024

    49/100
    • ECI118.1
    • Price$0.10 / $0.10
    • Context128K
    Full specs Remove Ministral 3B

  2. Mistral AI

    Mixtral 8x7B

    Released Dec 11, 2023

    37/100
    • ECI118.5
    • Price$0.70 / $0.70
    • Context32K
    Full specs Remove Mixtral 8x7B

  3. Meta

    Llama-3.1-8B-Instruct

    Released Jul 23, 2024

    46/100
    • ECI116.6
    • Price$0.152 / $0.167
    • Context128K
    Full specs Remove Llama-3.1-8B-Instruct
01 — Verdict

Ministral 3B is our pick

Ministral 3B is the better all-round choice, scoring 49/100 against Llama-3.1-8B-Instruct (46) and Mixtral 8x7B (37). It leads on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityMixtral 8x7BCapabilities Index (ECI): Mixtral 8x7B 118.5 · Ministral 3B 118.1 · Llama-3.1-8B-Instruct 116.6
  • Lowest priceMinistral 3BMinistral 3B $0.10 · Llama-3.1-8B-Instruct $0.156 · Mixtral 8x7B $0.70 per 1M tokens (3:1 blend)
  • Longest contextMinistral 3B and Llama-3.1-8B-InstructMinistral 3B 128,000 · Llama-3.1-8B-Instruct 128,000 · Mixtral 8x7B 32,000 tokens
  • Widest inputsSame inputsMinistral 3B: Text · Mixtral 8x7B: Text · Llama-3.1-8B-Instruct: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightMinistral 3BMixtral 8x7BLlama-3.1-8B-Instruct
CapabilityCapabilities Index (ECI)50%383836
Price25%975788
Inputs & features15%252525
Context window10%24024
Overall100%49/10037/10046/100
02 — Side by side

Every spec in one table

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

Ministral 3B vs Mixtral 8x7B vs Llama-3.1-8B-Instruct specifications side by side
SpecificationMinistral 3BMistral AIMixtral 8x7BMistral AILlama-3.1-8B-InstructMeta
Capability
Capabilities Index (ECI)118.1118.5 (best)116.6
ECI rank#144 of 148#142 of 148 (best)#145 of 148
GPQA DiamondGraduate-level science questions25.3%30.6% (best)27.0%
OTIS Mock AIME 2024–2025Competition mathematics——1.7%
Price per million tokens
Input$0.10 (best)$0.70$0.152
Output$0.10 (best)$0.70$0.167
Cached input———
Blended (3:1)$0.10 (best)$0.70$0.156
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersOfficial Mistral APIMedian of 9 providers
Limits
Context window128,000 tokens (best)32,000 tokens128,000 tokens (best)
Max output8,192 tokens32,000 tokens (best)4,096 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenOpen
API model ID—open-mixtral-8x7b—
API providers119 (best)
ReleasedOct 16, 2024Dec 11, 2023Jul 23, 2024
Knowledge cutoffMar 2024Jan 2024Dec 2023
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.

  • Ministral 3B$1.20
  • Mixtral 8x7B$8.40
  • Llama-3.1-8B-Instruct$1.85
04 — Questions

Which should you choose?

Which is better: Ministral 3B, Mixtral 8x7B or Llama-3.1-8B-Instruct?

Ministral 3B is the better all-round choice, scoring 49/100 against Llama-3.1-8B-Instruct (46) and Mixtral 8x7B (37). It leads on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Ministral 3B, Mixtral 8x7B or Llama-3.1-8B-Instruct?

Ministral 3B is cheaper at $0.10 input / $0.10 output per million tokens (median across 1 API provider). Llama-3.1-8B-Instruct costs $0.152 input / $0.167 output per million tokens (median across 9 API providers); Mixtral 8x7B costs $0.70 input / $0.70 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.10 per million tokens for Ministral 3B versus $0.156 for Llama-3.1-8B-Instruct (1.6× as much) and $0.70 for Mixtral 8x7B (7× as much).

Which scores higher on benchmarks?

Mixtral 8x7B scores higher on the Capabilities Index (ECI): Mixtral 8x7B 118.5 (#142 of 148), Ministral 3B 118.1 (#144 of 148) and Llama-3.1-8B-Instruct 116.6 (#145 of 148). The confidence ranges of the top two overlap (111.3–121.3 vs 107.4–121.8), so treat the gap as small. On individual benchmarks: GPQA Diamond — Mixtral 8x7B 30.6%, Llama-3.1-8B-Instruct 27.0%, Ministral 3B 25.3%.

Which is better for coding?

There are no published SWE-bench Verified results for Ministral 3B, Mixtral 8x7B and Llama-3.1-8B-Instruct yet, so there is no like-for-like coding score. On overall capability, Mixtral 8x7B 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?

Ministral 3B and Llama-3.1-8B-Instruct have the largest context windows (128,000 and 128,000 tokens), against 32,000 for Mixtral 8x7B. Maximum output per response: Ministral 3B up to 8,192, Mixtral 8x7B up to 32,000, Llama-3.1-8B-Instruct up to 4,096 tokens.

Which can read images, PDFs, audio or video?

Ministral 3B accepts text; Mixtral 8x7B accepts text; Llama-3.1-8B-Instruct accepts text. They handle the same number of input types.

Are any of these open source?

Yes, all three publish their weights, so you can self-host them.

Which is newer?

Ministral 3B is the newest, released Oct 16, 2024. Llama-3.1-8B-Instruct came out Jul 23, 2024; Mixtral 8x7B came out Dec 11, 2023. Knowledge cutoff: Ministral 3B Mar 2024, Mixtral 8x7B Jan 2024, Llama-3.1-8B-Instruct Dec 2023.

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