ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Llama-3.1-8B-Instruct vs Ministral 3B vs Mistral Small 3.2

Mistral Small 3.2 comes out ahead, 60 to 49 and 46 on our weighted score, though Ministral 3B is 33% cheaper per token.

  1. 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

  2. Mistral AI

    Ministral 3B

    Released Oct 16, 2024

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

    Mistral AI

    Mistral Small 3.2

    Released Jun 20, 2025

    60/100
    • ECI131.7
    • Price$0.10 / $0.30
    • Context128K
    Full specs Remove Mistral Small 3.2
01 — Verdict

Mistral Small 3.2 is our pick

Mistral Small 3.2 is the better all-round choice, scoring 60/100 against Ministral 3B (49) and Llama-3.1-8B-Instruct (46). It leads on capability and inputs & features. Ministral 3B wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityMistral Small 3.2Capabilities Index (ECI): Mistral Small 3.2 131.7 · Ministral 3B 118.1 · Llama-3.1-8B-Instruct 116.6
  • Lowest priceMinistral 3BMinistral 3B $0.10 · Mistral Small 3.2 $0.15 · Llama-3.1-8B-Instruct $0.156 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameLlama-3.1-8B-Instruct 128,000 · Ministral 3B 128,000 · Mistral Small 3.2 128,000 tokens
  • Widest inputsMistral Small 3.2Llama-3.1-8B-Instruct: Text · Ministral 3B: Text · Mistral Small 3.2: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightLlama-3.1-8B-InstructMinistral 3BMistral Small 3.2
CapabilityCapabilities Index (ECI)50%363855
Price25%889789
Inputs & features15%252550
Context window10%242424
Overall100%46/10049/10060/100
02 — Side by side

Every spec in one table

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

Llama-3.1-8B-Instruct vs Ministral 3B vs Mistral Small 3.2 specifications side by side
SpecificationLlama-3.1-8B-InstructMetaMinistral 3BMistral AIMistral Small 3.2Mistral AI
Capability
Capabilities Index (ECI)116.6118.1131.7 (best)
ECI rank#145 of 148#144 of 148#123 of 148 (best)
GPQA DiamondGraduate-level science questions27.0%25.3%49.1% (best)
OTIS Mock AIME 2024–2025Competition mathematics1.7%—30.3% (best)
Price per million tokens
Input$0.152$0.10 (best)$0.10 (best)
Output$0.167$0.10 (best)$0.30
Cached input———
Blended (3:1)$0.156$0.10 (best)$0.15
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 9 providersMedian of 1 providersOfficial Mistral API
Limits
Context window128,000 tokens128,000 tokens128,000 tokens
Max output4,096 tokens8,192 tokens16,384 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenOpen
API model ID——mistral-small-2506
API providers9 (best)16
ReleasedJul 23, 2024Oct 16, 2024Jun 20, 2025
Knowledge cutoffDec 2023Mar 2024Mar 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.

  • Llama-3.1-8B-Instruct$1.85
  • Ministral 3B$1.20
  • Mistral Small 3.2$1.60
04 — Questions

Which should you choose?

Which is better: Llama-3.1-8B-Instruct, Ministral 3B or Mistral Small 3.2?

Mistral Small 3.2 is the better all-round choice, scoring 60/100 against Ministral 3B (49) and Llama-3.1-8B-Instruct (46). It leads on capability and inputs & features. Ministral 3B wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Llama-3.1-8B-Instruct, Ministral 3B or Mistral Small 3.2?

Ministral 3B is cheaper at $0.10 input / $0.10 output per million tokens (median across 1 API provider). Mistral Small 3.2 costs $0.10 input / $0.30 output per million tokens (official Mistral API price); Llama-3.1-8B-Instruct costs $0.152 input / $0.167 output per million tokens (median across 9 API providers). At a typical mix of three input tokens to one output token, that is $0.10 per million tokens for Ministral 3B versus $0.15 for Mistral Small 3.2 (1.5× as much) and $0.156 for Llama-3.1-8B-Instruct (1.6× as much).

Which scores higher on benchmarks?

Mistral Small 3.2 scores higher on the Capabilities Index (ECI): Mistral Small 3.2 131.7 (#123 of 148), Ministral 3B 118.1 (#144 of 148) and Llama-3.1-8B-Instruct 116.6 (#145 of 148). Their confidence ranges do not overlap (126.6–133.9 vs 107.4–121.8), so the gap is a real one. On individual benchmarks: GPQA Diamond — Mistral Small 3.2 49.1%, 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 Llama-3.1-8B-Instruct, Ministral 3B and Mistral Small 3.2 yet, so there is no like-for-like coding score. On overall capability, Mistral Small 3.2 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?

Llama-3.1-8B-Instruct, Ministral 3B and Mistral Small 3.2 share the same 128,000-token context window. Maximum output per response: Llama-3.1-8B-Instruct up to 4,096, Ministral 3B up to 8,192, Mistral Small 3.2 up to 16,384 tokens.

Which can read images, PDFs, audio or video?

Llama-3.1-8B-Instruct accepts text; Ministral 3B accepts text; Mistral Small 3.2 accepts text and images. Mistral Small 3.2 handles the widest range of inputs.

Are any of these open source?

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

Which is newer?

Mistral Small 3.2 is the newest, released Jun 20, 2025. Ministral 3B came out Oct 16, 2024; Llama-3.1-8B-Instruct came out Jul 23, 2024. Knowledge cutoff: Llama-3.1-8B-Instruct Dec 2023, Ministral 3B Mar 2024, Mistral Small 3.2 Mar 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