ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Llama-3.3-70B-Instruct vs Ministral 3B vs Mistral Small 3.1 24B

Mistral Small 3.1 24B comes out ahead, 46 to 41 and 26 on our weighted score, though Ministral 3B is 4× cheaper per token.

Price in rating: Excluded · Include price

  1. Meta

    Llama-3.3-70B-Instruct

    Released Dec 6, 2024

    41/100
    • ECI126.2
    • Price$0.59 / $0.745
    • Context128K
  2. Mistral AI

    Ministral 3B

    Released Oct 16, 2024

    26/100
    • ECI—
    • Price$0.10 / $0.10
    • Context128K
  3. Our pick

    Mistral AI

    Mistral Small 3.1 24B

    Released Mar 17, 2025

    46/100
    • ECI—
    • Price$0.351 / $0.555
    • Context128K
01 — Verdict

Mistral Small 3.1 24B is our pick

Mistral Small 3.1 24B is the better all-round choice, scoring 46/100 against Llama-3.3-70B-Instruct (41) and Ministral 3B (26). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond), because Ministral 3B and Mistral Small 3.1 24B has no Capabilities Index score yet.

  • CapabilityMistral Small 3.1 24BShared benchmarks: Mistral Small 3.1 24B 47.5% · Llama-3.3-70B-Instruct 47.4% · Ministral 3B 25.3%
  • Lowest priceMinistral 3BMinistral 3B $0.10 · Mistral Small 3.1 24B $0.402 · Llama-3.3-70B-Instruct $0.629 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameLlama-3.3-70B-Instruct 128,000 · Ministral 3B 128,000 · Mistral Small 3.1 24B 128,000 tokens
  • Widest inputsMistral Small 3.1 24BLlama-3.3-70B-Instruct: Text · Ministral 3B: Text · Mistral Small 3.1 24B: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightLlama-3.3-70B-InstructMinistral 3BMistral Small 3.1 24B
CapabilityShared benchmarks67%472547
Inputs & features20%252550
Context window13%323232
Overall100%41/10026/10046/100
02 — Side by side

Every spec in one table

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

Llama-3.3-70B-Instruct vs Ministral 3B vs Mistral Small 3.1 24B specifications side by side
SpecificationLlama-3.3-70B-InstructMetaMinistral 3BMistral AIMistral Small 3.1 24BMistral AI
Capability
Capabilities Index (ECI)126.2——
ECI rank#144 of 158——
GPQA DiamondGraduate-level science questions47.4%25.3%47.5% (best)
OTIS Mock AIME 2024–2025Competition mathematics5.1%—5.8% (best)
Price per million tokens
Input$0.59$0.10 (best)$0.351
Output$0.745$0.10 (best)$0.555
Cached input———
Blended (3:1)$0.629$0.10 (best)$0.402
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 40 providersMedian of 1 providersMedian of 9 providers
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———
API providers43 (best)19
ReleasedDec 6, 2024Oct 16, 2024Mar 17, 2025
Knowledge cutoffDec 2023Mar 2024Jun 2024
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-3.3-70B-Instruct$7.39
  • Ministral 3B$1.20
  • Mistral Small 3.1 24B$4.62
04 — Questions

Which should you choose?

Which is better: Llama-3.3-70B-Instruct, Ministral 3B or Mistral Small 3.1 24B?

Mistral Small 3.1 24B is the better all-round choice, scoring 46/100 against Llama-3.3-70B-Instruct (41) and Ministral 3B (26). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond), because Ministral 3B and Mistral Small 3.1 24B has no Capabilities Index score yet.

Which is cheaper, Llama-3.3-70B-Instruct, Ministral 3B or Mistral Small 3.1 24B?

Ministral 3B is cheaper at $0.10 input / $0.10 output per million tokens (median across 1 API provider). Mistral Small 3.1 24B costs $0.351 input / $0.555 output per million tokens (median across 9 API providers); Llama-3.3-70B-Instruct costs $0.59 input / $0.745 output per million tokens (median across 40 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 $0.402 for Mistral Small 3.1 24B (4× as much) and $0.629 for Llama-3.3-70B-Instruct (6.3× 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): Mistral Small 3.1 24B 47.5%, Llama-3.3-70B-Instruct 47.4% and Ministral 3B 25.3%. On individual benchmarks: GPQA Diamond — Mistral Small 3.1 24B 47.5%, Llama-3.3-70B-Instruct 47.4%, Ministral 3B 25.3%.

Which is better for coding?

There are no published SWE-bench Verified results for Llama-3.3-70B-Instruct, Ministral 3B and Mistral Small 3.1 24B yet, so there is no like-for-like coding score. On overall capability, Mistral Small 3.1 24B 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-3.3-70B-Instruct, Ministral 3B and Mistral Small 3.1 24B share the same 128,000-token context window. Maximum output per response: Llama-3.3-70B-Instruct up to 4,096, Ministral 3B up to 8,192, Mistral Small 3.1 24B up to 16,384 tokens.

Which can read images, PDFs, audio or video?

Llama-3.3-70B-Instruct accepts text; Ministral 3B accepts text; Mistral Small 3.1 24B accepts text and images. Mistral Small 3.1 24B 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 3.1 24B is the newest, released Mar 17, 2025. Llama-3.3-70B-Instruct came out Dec 6, 2024; Ministral 3B came out Oct 16, 2024. Knowledge cutoff: Llama-3.3-70B-Instruct Dec 2023, Ministral 3B Mar 2024, Mistral Small 3.1 24B Jun 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.