ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Codestral 25.08 vs ERNIE 4.5 300B A47B vs Mistral Medium 3.1

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

    Codestral 25.08

    Released Jul 30, 2025

    49/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
  2. Baidu

    ERNIE 4.5 300B A47B

    Released Jun 30, 2025

    45/100
    • ECI—
    • Price$0.28 / $1.10
    • Context131K
  3. Mistral AI

    Mistral Medium 3.1

    Released Aug 12, 2025

    50/100
    • ECI—
    • Price$0.44 / $2.20
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Medium 3.1 50/100, Codestral 25.08 49/100, ERNIE 4.5 300B A47B 45/100) 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 priceCodestral 25.08Codestral 25.08 $0.45 · ERNIE 4.5 300B A47B $0.485 · Mistral Medium 3.1 $0.88 per 1M tokens (3:1 blend)
  • Longest contextERNIE 4.5 300B A47B and Mistral Medium 3.1ERNIE 4.5 300B A47B 131,072 · Mistral Medium 3.1 131,072 · Codestral 25.08 128,000 tokens
  • Widest inputsMistral Medium 3.1Codestral 25.08: Text · ERNIE 4.5 300B A47B: Text · Mistral Medium 3.1: Text, Images, PDFs
  • Self-hostingERNIE 4.5 300B A47BPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightCodestral 25.08ERNIE 4.5 300B A47BMistral Medium 3.1
Price50%636250
Inputs & features30%352560
Context window20%323232
Specs & price only100%49/10045/10050/100

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.

Codestral 25.08 vs ERNIE 4.5 300B A47B vs Mistral Medium 3.1 specifications side by side
SpecificationCodestral 25.08Mistral AIERNIE 4.5 300B A47BBaiduMistral Medium 3.1Mistral AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30$0.28 (best)$0.44
Output$0.90 (best)$1.10$2.20
Cached input$0.03——
Blended (3:1)$0.45 (best)$0.485$0.88
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIMedian of 1 providersMedian of 4 providers
Limits
Context window128,000 tokens131,072 tokens (best)131,072 tokens (best)
Max output8,192 tokens12,000 tokens104,857 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenApache-2.0Proprietary
API model IDcodestral-2508——
API providers11 (best)14
ReleasedJul 30, 2025Jun 30, 2025Aug 12, 2025
Knowledge cutoff——Jun 30, 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.

  • Codestral 25.08$4.80
  • ERNIE 4.5 300B A47B$5.00
  • Mistral Medium 3.1$8.80
04 — Questions

Which should you choose?

Which is better: Codestral 25.08, ERNIE 4.5 300B A47B or Mistral Medium 3.1?

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Medium 3.1 50/100, Codestral 25.08 49/100, ERNIE 4.5 300B A47B 45/100) 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, Codestral 25.08, ERNIE 4.5 300B A47B or Mistral Medium 3.1?

Codestral 25.08 is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). ERNIE 4.5 300B A47B costs $0.28 input / $1.10 output per million tokens (median across 1 API provider); Mistral Medium 3.1 costs $0.44 input / $2.20 output per million tokens (median across 4 API providers). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral 25.08 versus $0.485 for ERNIE 4.5 300B A47B (1.1× as much) and $0.88 for Mistral Medium 3.1 (2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Codestral 25.08 has not been scored yet, ERNIE 4.5 300B A47B has not been scored yet and Mistral Medium 3.1 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Codestral 25.08, ERNIE 4.5 300B A47B and Mistral Medium 3.1 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?

ERNIE 4.5 300B A47B and Mistral Medium 3.1 have the largest context windows (131,072 and 131,072 tokens), against 128,000 for Codestral 25.08. Maximum output per response: Codestral 25.08 up to 8,192, ERNIE 4.5 300B A47B up to 12,000, Mistral Medium 3.1 up to 104,857 tokens.

Which can read images, PDFs, audio or video?

Codestral 25.08 accepts text; ERNIE 4.5 300B A47B accepts text; Mistral Medium 3.1 accepts text, images and PDFs. Mistral Medium 3.1 handles the widest range of inputs.

Are any of these open source?

ERNIE 4.5 300B A47B publishes its weights (Apache-2.0) and can be self-hosted; Codestral 25.08 and Mistral Medium 3.1 is proprietary.

Which is newer?

Mistral Medium 3.1 is the newest, released Aug 12, 2025. Codestral 25.08 came out Jul 30, 2025; ERNIE 4.5 300B A47B came out Jun 30, 2025. Knowledge cutoff: Mistral Medium 3.1 Jun 30, 2025.

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.