ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-5.1 Codex mini vs Qwen3-VL Plus vs Mistral Large 3

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. OpenAI

    GPT-5.1 Codex mini

    Released Nov 13, 2025

    56/100
    • ECI—
    • Price$0.25 / $2.00
    • Context400K
  2. Alibaba (Qwen)

    Qwen3-VL Plus

    Released Sep 23, 2025

    62/100
    • ECI—
    • Price$0.20 / $1.60
    • Context262K
  3. Mistral AI

    Mistral Large 3

    Released Dec 2, 2025

    53/100
    • ECI—
    • Price$0.50 / $1.50
    • Context262K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3-VL Plus 62/100, GPT-5.1 Codex mini 56/100, Mistral Large 3 53/100) 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 priceQwen3-VL PlusQwen3-VL Plus $0.55 · GPT-5.1 Codex mini $0.688 · Mistral Large 3 $0.75 per 1M tokens (3:1 blend)
  • Longest contextGPT-5.1 Codex miniGPT-5.1 Codex mini 400,000 · Qwen3-VL Plus 262,144 · Mistral Large 3 262,144 tokens
  • Widest inputsQwen3-VL PlusGPT-5.1 Codex mini: Text, Images · Qwen3-VL Plus: Text, Images, Video · Mistral Large 3: Text, Images
  • Self-hostingMistral Large 3Publishes downloadable weights
How the score is built
MeasureWeightGPT-5.1 Codex miniQwen3-VL PlusMistral Large 3
Price50%556053
Inputs & features30%608060
Context window20%504343
Specs & price only100%56/10062/10053/100

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.

GPT-5.1 Codex mini vs Qwen3-VL Plus vs Mistral Large 3 specifications side by side
SpecificationGPT-5.1 Codex miniOpenAIQwen3-VL PlusAlibaba (Qwen)Mistral Large 3Mistral AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.25$0.20 (best)$0.50
Output$2.00$1.60$1.50 (best)
Cached input—$0.04 (best)$0.05
Blended (3:1)$0.688$0.55 (best)$0.75
Long-context rateSame rateOver 32K: $0.30 / $2.40Same rate
Price sourceMedian of 16 providersOfficial Alibaba APIOfficial Mistral API
Limits
Context window400,000 tokens (best)262,144 tokens262,144 tokens
Max output128,000 tokens32,768 tokens262,144 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoYesNo
ReasoningYesYesNo
Tool callingYesYesYes
Structured outputNoYesYes
Availability
WeightsProprietaryProprietaryOpen
API model ID—qwen3-vl-plusmistral-large-2512
API providers16 (best)715
ReleasedNov 13, 2025Sep 23, 2025Dec 2, 2025
Knowledge cutoffSep 30, 2024Apr 2025Nov 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.

  • GPT-5.1 Codex mini$6.50
  • Qwen3-VL Plus$5.20
  • Mistral Large 3$8.00
04 — Questions

Which should you choose?

Which is better: GPT-5.1 Codex mini, Qwen3-VL Plus or Mistral Large 3?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3-VL Plus 62/100, GPT-5.1 Codex mini 56/100, Mistral Large 3 53/100) 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, GPT-5.1 Codex mini, Qwen3-VL Plus or Mistral Large 3?

Qwen3-VL Plus is cheaper at $0.20 input / $1.60 output per million tokens (official Alibaba API price). GPT-5.1 Codex mini costs $0.25 input / $2.00 output per million tokens (median across 16 API providers); Mistral Large 3 costs $0.50 input / $1.50 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.55 per million tokens for Qwen3-VL Plus versus $0.688 for GPT-5.1 Codex mini (1.3× as much) and $0.75 for Mistral Large 3 (1.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GPT-5.1 Codex mini has not been scored yet, Qwen3-VL Plus has not been scored yet and Mistral Large 3 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-5.1 Codex mini, Qwen3-VL Plus and Mistral Large 3 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?

GPT-5.1 Codex mini has the largest context window at 400,000 tokens, against 262,144 for Qwen3-VL Plus and 262,144 for Mistral Large 3. Maximum output per response: GPT-5.1 Codex mini up to 128,000, Qwen3-VL Plus up to 32,768, Mistral Large 3 up to 262,144 tokens.

Which can read images, PDFs, audio or video?

GPT-5.1 Codex mini accepts text and images; Qwen3-VL Plus accepts text, images and video; Mistral Large 3 accepts text and images. Qwen3-VL Plus handles the widest range of inputs.

Are any of these open source?

Mistral Large 3 publishes its weights and can be self-hosted; GPT-5.1 Codex mini and Qwen3-VL Plus is proprietary.

Which is newer?

Mistral Large 3 is the newest, released Dec 2, 2025. GPT-5.1 Codex mini came out Nov 13, 2025; Qwen3-VL Plus came out Sep 23, 2025. Knowledge cutoff: GPT-5.1 Codex mini Sep 30, 2024, Qwen3-VL Plus Apr 2025, Mistral Large 3 Nov 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.