ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Mistral Small 3.2 24B vs Phi-4-mini vs ERNIE 4.5 21B A3B

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Mistral AI

    Mistral Small 3.2 24B

    Released Jun 20, 2025

    68/100
    • ECI—
    • Price$0.087 / $0.231
    • Context256K
  2. Microsoft

    Phi-4-mini

    Released Feb 26, 2025

    58/100
    • ECI—
    • Price$0.075 / $0.30
    • Context128K
  3. Baidu

    ERNIE 4.5 21B A3B

    Released Jun 30, 2025

    59/100
    • ECI—
    • Price$0.07 / $0.28
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Small 3.2 24B 68/100, ERNIE 4.5 21B A3B 59/100, Phi-4-mini 58/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceERNIE 4.5 21B A3BERNIE 4.5 21B A3B $0.122 · Mistral Small 3.2 24B $0.123 · Phi-4-mini $0.131 per 1M tokens (3:1 blend)
  • Longest contextMistral Small 3.2 24BMistral Small 3.2 24B 256,000 · ERNIE 4.5 21B A3B 131,072 · Phi-4-mini 128,000 tokens
  • Widest inputsMistral Small 3.2 24BMistral Small 3.2 24B: Text, Images · Phi-4-mini: Text · ERNIE 4.5 21B A3B: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightMistral Small 3.2 24BPhi-4-miniERNIE 4.5 21B A3B
Price50%898889
Inputs & features30%502525
Context window20%433232
Specs & price only100%68/10058/10059/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

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

Mistral Small 3.2 24B vs Phi-4-mini vs ERNIE 4.5 21B A3B specifications side by side
SpecificationMistral Small 3.2 24BMistral AIPhi-4-miniMicrosoftERNIE 4.5 21B A3BBaidu
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.087$0.075$0.07 (best)
Output$0.231 (best)$0.30$0.28
Cached input———
Blended (3:1)$0.123$0.131$0.122 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 8 providersOfficial Azure APIMedian of 1 providers
Limits
Context window256,000 tokens (best)128,000 tokens131,072 tokens
Max output16,384 tokens (best)4,096 tokens8,000 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenOpenApache-2.0
API model ID—phi-4-mini—
API providers8 (best)21
ReleasedJun 20, 2025Feb 26, 2025Jun 30, 2025
Knowledge cutoffOct 31, 2023Jun 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.

  • Mistral Small 3.2 24B$1.33
  • Phi-4-mini$1.35
  • ERNIE 4.5 21B A3B$1.26
04 — Questions

Which should you choose?

Which is better: Mistral Small 3.2 24B, Phi-4-mini or ERNIE 4.5 21B A3B?

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Small 3.2 24B 68/100, ERNIE 4.5 21B A3B 59/100, Phi-4-mini 58/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Mistral Small 3.2 24B, Phi-4-mini or ERNIE 4.5 21B A3B?

ERNIE 4.5 21B A3B is cheaper at $0.07 input / $0.28 output per million tokens (median across 1 API provider). Mistral Small 3.2 24B costs $0.087 input / $0.231 output per million tokens (median across 8 API providers); Phi-4-mini costs $0.075 input / $0.30 output per million tokens (official Azure API price). At a typical mix of three input tokens to one output token, that is $0.122 per million tokens for ERNIE 4.5 21B A3B versus $0.123 for Mistral Small 3.2 24B (1× as much) and $0.131 for Phi-4-mini (1.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Mistral Small 3.2 24B has not been scored yet, Phi-4-mini has not been scored yet and ERNIE 4.5 21B A3B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Mistral Small 3.2 24B, Phi-4-mini and ERNIE 4.5 21B A3B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Mistral Small 3.2 24B has the largest context window at 256,000 tokens, against 131,072 for ERNIE 4.5 21B A3B and 128,000 for Phi-4-mini. Maximum output per response: Mistral Small 3.2 24B up to 16,384, Phi-4-mini up to 4,096, ERNIE 4.5 21B A3B up to 8,000 tokens.

Which can read images, PDFs, audio or video?

Mistral Small 3.2 24B accepts text and images; Phi-4-mini accepts text; ERNIE 4.5 21B A3B accepts text. Mistral Small 3.2 24B handles the widest range of inputs.

Are any of these open source?

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

Which is newer?

ERNIE 4.5 21B A3B is the newest, released Jun 30, 2025. Mistral Small 3.2 24B came out Jun 20, 2025; Phi-4-mini came out Feb 26, 2025. Knowledge cutoff: Mistral Small 3.2 24B Oct 31, 2023, Phi-4-mini Jun 2024.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.