ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Qwen3-Coder 480B-A35B Instruct vs Codestral 25.08 vs o4-mini-deep-research

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. Alibaba (Qwen)

    Qwen3-Coder 480B-A35B Instruct

    Released Jul 22, 2025Deprecated

    29/100
    • ECI—
    • Price$1.50 / $7.50
    • Context262K
  2. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025

    49/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
  3. OpenAI

    o4-mini-deep-research

    Released Jun 26, 2025

    38/100
    • ECI—
    • Price$1.80 / $7.20
    • Context200K
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, o4-mini-deep-research 38/100, Qwen3-Coder 480B-A35B Instruct 29/100) 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 · Qwen3-Coder 480B-A35B Instruct $3.00 · o4-mini-deep-research $3.15 per 1M tokens (3:1 blend)
  • Longest contextQwen3-Coder 480B-A35B InstructQwen3-Coder 480B-A35B Instruct 262,144 · o4-mini-deep-research 200,000 · Codestral 25.08 128,000 tokens
  • Widest inputso4-mini-deep-researchQwen3-Coder 480B-A35B Instruct: Text · Codestral 25.08: Text · o4-mini-deep-research: Text, Images
  • Self-hostingQwen3-Coder 480B-A35B InstructPublishes downloadable weights
How the score is built
MeasureWeightQwen3-Coder 480B-A35B InstructCodestral 25.08o4-mini-deep-research
Price50%266325
Inputs & features30%253560
Context window20%433239
Specs & price only100%29/10049/10038/100

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.

Qwen3-Coder 480B-A35B Instruct vs Codestral 25.08 vs o4-mini-deep-research specifications side by side
SpecificationQwen3-Coder 480B-A35B InstructAlibaba (Qwen)Codestral 25.08Mistral AIo4-mini-deep-researchOpenAI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$1.50$0.30 (best)$1.80
Output$7.50$0.90 (best)$7.20
Cached input—$0.03—
Blended (3:1)$3.00$0.45 (best)$3.15
Long-context rateOver 32K: $2.70 / $13.50Same rateSame rate
Price sourceOfficial Alibaba APIOfficial Mistral APIMedian of 1 providers
Limits
Context window262,144 tokens (best)128,000 tokens200,000 tokens
Max output65,536 tokens8,192 tokens100,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenProprietaryProprietary
API model IDqwen3-coder-480b-a35b-instructcodestral-2508—
API providers24 (best)111
ReleasedJul 22, 2025Jul 30, 2025Jun 26, 2025
Knowledge cutoffApr 2025—May 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.

  • Qwen3-Coder 480B-A35B Instruct$30.00
  • Codestral 25.08$4.80
  • o4-mini-deep-research$32.40
04 — Questions

Which should you choose?

Which is better: Qwen3-Coder 480B-A35B Instruct, Codestral 25.08 or o4-mini-deep-research?

There is not enough shared capability evidence to name an overall winner. The scores (Codestral 25.08 49/100, o4-mini-deep-research 38/100, Qwen3-Coder 480B-A35B Instruct 29/100) 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, Qwen3-Coder 480B-A35B Instruct, Codestral 25.08 or o4-mini-deep-research?

Codestral 25.08 is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen3-Coder 480B-A35B Instruct costs $1.50 input / $7.50 output per million tokens (official Alibaba API price); o4-mini-deep-research costs $1.80 input / $7.20 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral 25.08 versus $3.00 for Qwen3-Coder 480B-A35B Instruct (6.7× as much) and $3.15 for o4-mini-deep-research (7× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Qwen3-Coder 480B-A35B Instruct has not been scored yet, Codestral 25.08 has not been scored yet and o4-mini-deep-research has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3-Coder 480B-A35B Instruct, Codestral 25.08 and o4-mini-deep-research 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 480B-A35B Instruct has the largest context window at 262,144 tokens, against 200,000 for o4-mini-deep-research and 128,000 for Codestral 25.08. Maximum output per response: Qwen3-Coder 480B-A35B Instruct up to 65,536, Codestral 25.08 up to 8,192, o4-mini-deep-research up to 100,000 tokens.

Which can read images, PDFs, audio or video?

Qwen3-Coder 480B-A35B Instruct accepts text; Codestral 25.08 accepts text; o4-mini-deep-research accepts text and images. o4-mini-deep-research handles the widest range of inputs.

Are any of these open source?

Qwen3-Coder 480B-A35B Instruct publishes its weights and can be self-hosted; Codestral 25.08 and o4-mini-deep-research is proprietary.

Which is newer?

Codestral 25.08 is the newest, released Jul 30, 2025. Qwen3-Coder 480B-A35B Instruct came out Jul 22, 2025; o4-mini-deep-research came out Jun 26, 2025. Knowledge cutoff: Qwen3-Coder 480B-A35B Instruct Apr 2025, o4-mini-deep-research May 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.