ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Codestral 25.08 vs ERNIE 4.5 300B A47B vs Qwen3-VL Plus

Qwen3-VL Plus comes out ahead, 58 to 47 and 43 on our weighted score, though Codestral 25.08 is 18% cheaper per token.

  1. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025

    47/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
    Full specs Remove Codestral 25.08

  2. Baidu

    ERNIE 4.5 300B A47B

    Released Jun 30, 2025

    43/100
    • ECI—
    • Price$0.28 / $1.10
    • Context131K
    Full specs Remove ERNIE 4.5 300B A47B
  3. Our pick

    Alibaba (Qwen)

    Qwen3-VL Plus

    Released Sep 23, 2025

    58/100
    • ECI—
    • Price$0.20 / $1.60
    • Context262K
    Full specs Remove Qwen3-VL Plus
01 — Verdict

Qwen3-VL Plus is our pick

Qwen3-VL Plus is the better all-round choice, scoring 58/100 against Codestral 25.08 (47) and ERNIE 4.5 300B A47B (43). It leads on inputs & features and context window. 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-VL Plus $0.55 per 1M tokens (3:1 blend)
  • Longest contextQwen3-VL PlusQwen3-VL Plus 262,144 · ERNIE 4.5 300B A47B 131,072 · Codestral 25.08 128,000 tokens
  • Widest inputsQwen3-VL PlusCodestral 25.08: Text · ERNIE 4.5 300B A47B: Text · Qwen3-VL Plus: Text, Images
  • Self-hostingERNIE 4.5 300B A47BPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightCodestral 25.08ERNIE 4.5 300B A47BQwen3-VL Plus
Price50%646260
Inputs & features30%352570
Context window20%242537
Overall100%47/10043/10058/100

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 Qwen3-VL Plus specifications side by side
SpecificationCodestral 25.08Mistral AIERNIE 4.5 300B A47BBaiduQwen3-VL PlusAlibaba (Qwen)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30$0.28$0.20 (best)
Output$0.90 (best)$1.10$1.60
Cached input$0.03 (best)—$0.04
Blended (3:1)$0.45 (best)$0.485$0.55
Long-context rateSame rateSame rateOver 32K: $0.30 / $2.40
Price sourceOfficial Mistral APIMedian of 1 providersOfficial Alibaba API
Limits
Context window128,000 tokens131,072 tokens262,144 tokens (best)
Max output8,192 tokens12,000 tokens32,768 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoYes
Tool callingYesYesYes
Structured outputYesNoYes
Availability
WeightsProprietaryOpenApache-2.0Proprietary
API model IDcodestral-2508—qwen3-vl-plus
API providers11 (best)16
ReleasedJul 30, 2025Jun 30, 2025Sep 23, 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.

  • Codestral 25.08$4.80
  • ERNIE 4.5 300B A47B$5.00
  • Qwen3-VL Plus$5.20
04 — Questions

Which should you choose?

Which is better: Codestral 25.08, ERNIE 4.5 300B A47B or Qwen3-VL Plus?

Qwen3-VL Plus is the better all-round choice, scoring 58/100 against Codestral 25.08 (47) and ERNIE 4.5 300B A47B (43). It leads on inputs & features and context window. 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 Qwen3-VL Plus?

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-VL Plus costs $0.20 input / $1.60 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 $0.55 for Qwen3-VL Plus (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 Qwen3-VL Plus 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 Qwen3-VL Plus 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-VL Plus 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: Codestral 25.08 up to 8,192, ERNIE 4.5 300B A47B up to 12,000, Qwen3-VL Plus up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Codestral 25.08 accepts text; ERNIE 4.5 300B A47B accepts text; Qwen3-VL Plus accepts text and images. Qwen3-VL Plus 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 Qwen3-VL Plus is proprietary.

Which is newer?

Qwen3-VL Plus is the newest, released Sep 23, 2025. Codestral 25.08 came out Jul 30, 2025; ERNIE 4.5 300B A47B came out Jun 30, 2025. Knowledge cutoff: Qwen3-VL Plus Apr 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 Nov 2, 2026.

05 — Keep comparing

Related comparisons