ZMIME
Comparison · 3 models · Updated Nov 18, 2026

ERNIE 4.5 300B A47B vs Qwen3-Coder 30B-A3B Instruct vs Codestral 25.08

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. Baidu

    ERNIE 4.5 300B A47B

    Released Jun 30, 2025

    45/100
    • ECI—
    • Price$0.28 / $1.10
    • Context131K
  2. Alibaba (Qwen)

    Qwen3-Coder 30B-A3B Instruct

    Released Jul 31, 2025Deprecated

    41/100
    • ECI—
    • Price$0.45 / $2.25
    • Context262K
  3. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025

    49/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Codestral 25.08 49/100, ERNIE 4.5 300B A47B 45/100, Qwen3-Coder 30B-A3B Instruct 41/100) 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 · Qwen3-Coder 30B-A3B Instruct $0.90 per 1M tokens (3:1 blend)
  • Longest contextQwen3-Coder 30B-A3B InstructQwen3-Coder 30B-A3B Instruct 262,144 · ERNIE 4.5 300B A47B 131,072 · Codestral 25.08 128,000 tokens
  • Widest inputsSame inputsERNIE 4.5 300B A47B: Text · Qwen3-Coder 30B-A3B Instruct: Text · Codestral 25.08: Text
  • Self-hostingERNIE 4.5 300B A47B and Qwen3-Coder 30B-A3B InstructPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightERNIE 4.5 300B A47BQwen3-Coder 30B-A3B InstructCodestral 25.08
Price50%625063
Inputs & features30%252535
Context window20%324332
Specs & price only100%45/10041/10049/100

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.

ERNIE 4.5 300B A47B vs Qwen3-Coder 30B-A3B Instruct vs Codestral 25.08 specifications side by side
SpecificationERNIE 4.5 300B A47BBaiduQwen3-Coder 30B-A3B InstructAlibaba (Qwen)Codestral 25.08Mistral AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.28 (best)$0.45$0.30
Output$1.10$2.25$0.90 (best)
Cached input——$0.03
Blended (3:1)$0.485$0.90$0.45 (best)
Long-context rateSame rateOver 32K: $0.75 / $3.75Same rate
Price sourceMedian of 1 providersOfficial Alibaba APIOfficial Mistral API
Limits
Context window131,072 tokens262,144 tokens (best)128,000 tokens
Max output12,000 tokens65,536 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenApache-2.0OpenProprietary
API model ID—qwen3-coder-30b-a3b-instructcodestral-2508
API providers118 (best)11
ReleasedJun 30, 2025Jul 31, 2025Jul 30, 2025
Knowledge cutoff—Apr 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.

  • ERNIE 4.5 300B A47B$5.00
  • Qwen3-Coder 30B-A3B Instruct$9.00
  • Codestral 25.08$4.80
04 — Questions

Which should you choose?

Which is better: ERNIE 4.5 300B A47B, Qwen3-Coder 30B-A3B Instruct or Codestral 25.08?

There is not enough shared capability evidence to name an overall winner. The scores (Codestral 25.08 49/100, ERNIE 4.5 300B A47B 45/100, Qwen3-Coder 30B-A3B Instruct 41/100) 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, ERNIE 4.5 300B A47B, Qwen3-Coder 30B-A3B Instruct or Codestral 25.08?

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); Qwen3-Coder 30B-A3B Instruct costs $0.45 input / $2.25 output per million tokens (official Alibaba API price). 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 $0.90 for Qwen3-Coder 30B-A3B Instruct (2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. ERNIE 4.5 300B A47B has not been scored yet, Qwen3-Coder 30B-A3B Instruct has not been scored yet and Codestral 25.08 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for ERNIE 4.5 300B A47B, Qwen3-Coder 30B-A3B Instruct and Codestral 25.08 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?

Qwen3-Coder 30B-A3B Instruct has the largest context window at 262,144 tokens, against 131,072 for ERNIE 4.5 300B A47B and 128,000 for Codestral 25.08. Maximum output per response: ERNIE 4.5 300B A47B up to 12,000, Qwen3-Coder 30B-A3B Instruct up to 65,536, Codestral 25.08 up to 8,192 tokens.

Which can read images, PDFs, audio or video?

ERNIE 4.5 300B A47B accepts text; Qwen3-Coder 30B-A3B Instruct accepts text; Codestral 25.08 accepts text. They handle the same number of input types.

Are any of these open source?

ERNIE 4.5 300B A47B and Qwen3-Coder 30B-A3B Instruct publishes its weights (Apache-2.0) and can be self-hosted; Codestral 25.08 is proprietary.

Which is newer?

Qwen3-Coder 30B-A3B Instruct is the newest, released Jul 31, 2025. Codestral 25.08 came out Jul 30, 2025; ERNIE 4.5 300B A47B came out Jun 30, 2025. Knowledge cutoff: Qwen3-Coder 30B-A3B Instruct Apr 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.