ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-5 Chat vs GPT-5.1 Codex mini vs Qwen MT Plus

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 Chat

    Released Aug 7, 2025

    32/100
    • ECI—
    • Price$1.25 / $10.00
    • Context400K
  2. OpenAI

    GPT-5.1 Codex mini

    Released Nov 13, 2025

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

    Qwen MT Plus

    Released Jul 24, 2025

    11/100
    • ECI—
    • Price$2.46 / $7.37
    • Context16K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (GPT-5.1 Codex mini 56/100, GPT-5 Chat 32/100, Qwen MT Plus 11/100) 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 priceGPT-5.1 Codex miniGPT-5.1 Codex mini $0.688 · GPT-5 Chat $3.44 · Qwen MT Plus $3.69 per 1M tokens (3:1 blend)
  • Longest contextGPT-5 Chat and GPT-5.1 Codex miniGPT-5 Chat 400,000 · GPT-5.1 Codex mini 400,000 · Qwen MT Plus 16,384 tokens
  • Widest inputsGPT-5 Chat and GPT-5.1 Codex miniGPT-5 Chat: Text, Images · GPT-5.1 Codex mini: Text, Images · Qwen MT Plus: Text
  • Self-hostingNo confirmed open weightsAll three are available only through APIs
How the score is built
MeasureWeightGPT-5 ChatGPT-5.1 Codex miniQwen MT Plus
Price50%235522
Inputs & features30%35600
Context window20%50500
Specs & price only100%32/10056/10011/100

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 Chat vs GPT-5.1 Codex mini vs Qwen MT Plus specifications side by side
SpecificationGPT-5 ChatOpenAIGPT-5.1 Codex miniOpenAIQwen MT PlusAlibaba (Qwen)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$1.25$0.25 (best)$2.46
Output$10.00$2.00 (best)$7.37
Cached input———
Blended (3:1)$3.44$0.688 (best)$3.69
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 5 providersMedian of 16 providersOfficial Alibaba API
Limits
Context window400,000 tokens (best)400,000 tokens (best)16,384 tokens
Max output128,000 tokens (best)128,000 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesNo
Tool callingNoYesNo
Structured outputNoNoNo
Availability
WeightsProprietaryProprietaryProprietary
API model ID——qwen-mt-plus
API providers516 (best)3
ReleasedAug 7, 2025Nov 13, 2025Jul 24, 2025
Knowledge cutoffSep 30, 2024Sep 30, 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 Chat$32.50
  • GPT-5.1 Codex mini$6.50
  • Qwen MT Plus$39.34
04 — Questions

Which should you choose?

Which is better: GPT-5 Chat, GPT-5.1 Codex mini or Qwen MT Plus?

There is not enough shared capability evidence to name an overall winner. The scores (GPT-5.1 Codex mini 56/100, GPT-5 Chat 32/100, Qwen MT Plus 11/100) 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 Chat, GPT-5.1 Codex mini or Qwen MT Plus?

GPT-5.1 Codex mini is cheaper at $0.25 input / $2.00 output per million tokens (median across 16 API providers). GPT-5 Chat costs $1.25 input / $10.00 output per million tokens (median across 5 API providers); Qwen MT Plus costs $2.46 input / $7.37 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.688 per million tokens for GPT-5.1 Codex mini versus $3.44 for GPT-5 Chat (5× as much) and $3.69 for Qwen MT Plus (5.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GPT-5 Chat has not been scored yet, GPT-5.1 Codex mini has not been scored yet and Qwen MT Plus has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-5 Chat, GPT-5.1 Codex mini and Qwen MT Plus yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that GPT-5 Chat and Qwen MT Plus does not support tool calling, which most coding agents need.

Which has the bigger context window?

GPT-5 Chat and GPT-5.1 Codex mini have the largest context windows (400,000 and 400,000 tokens), against 16,384 for Qwen MT Plus. Maximum output per response: GPT-5 Chat up to 128,000, GPT-5.1 Codex mini up to 128,000, Qwen MT Plus up to 8,192 tokens.

Which can read images, PDFs, audio or video?

GPT-5 Chat accepts text and images; GPT-5.1 Codex mini accepts text and images; Qwen MT Plus accepts text. GPT-5 Chat handles the widest range of inputs.

Are any of these open source?

No. GPT-5 Chat, GPT-5.1 Codex mini and Qwen MT Plus are proprietary and only available through APIs and apps.

Which is newer?

GPT-5.1 Codex mini is the newest, released Nov 13, 2025. GPT-5 Chat came out Aug 7, 2025; Qwen MT Plus came out Jul 24, 2025. Knowledge cutoff: GPT-5 Chat Sep 30, 2024, GPT-5.1 Codex mini Sep 30, 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.