ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen3 VL 235B A22B Instruct vs Mistral Medium 3.1 vs MiniMax-M2

Qwen3 VL 235B A22B Instruct comes out ahead, 53 to 50 and 48 on our weighted score, though MiniMax-M2 is 14% cheaper per token.

  1. Our pick

    Alibaba (Qwen)

    Qwen3 VL 235B A22B Instruct

    Released Sep 23, 2025

    53/100
    • ECI—
    • Price$0.30 / $1.55
    • Context131K
    Full specs Remove Qwen3 VL 235B A22B Instruct

  2. Mistral AI

    Mistral Medium 3.1

    Released Aug 12, 2025

    50/100
    • ECI—
    • Price$0.40 / $2.00
    • Context262K
    Full specs Remove Mistral Medium 3.1

  3. MiniMax

    MiniMax-M2

    Released Oct 27, 2025

    48/100
    • ECI—
    • Price$0.30 / $1.20
    • Context205K
    Full specs Remove MiniMax-M2
01 — Verdict

Qwen3 VL 235B A22B Instruct is our pick

Qwen3 VL 235B A22B Instruct is the better all-round choice, scoring 53/100 against Mistral Medium 3.1 (50) and MiniMax-M2 (48). It leads on inputs & features. Mistral Medium 3.1 wins on context window. MiniMax-M2 wins on 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 priceMiniMax-M2MiniMax-M2 $0.525 · Qwen3 VL 235B A22B Instruct $0.613 · Mistral Medium 3.1 $0.80 per 1M tokens (3:1 blend)
  • Longest contextMistral Medium 3.1Mistral Medium 3.1 262,144 · MiniMax-M2 204,800 · Qwen3 VL 235B A22B Instruct 131,072 tokens
  • Widest inputsQwen3 VL 235B A22B Instruct and Mistral Medium 3.1Qwen3 VL 235B A22B Instruct: Text, Images · Mistral Medium 3.1: Text, Images · MiniMax-M2: Text
  • Self-hostingQwen3 VL 235B A22B Instruct and MiniMax-M2Publishes downloadable weights
How the score is built
MeasureWeightQwen3 VL 235B A22B InstructMistral Medium 3.1MiniMax-M2
Price50%605463
Inputs & features30%605035
Context window20%243732
Overall100%53/10050/10048/100

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 VL 235B A22B Instruct vs Mistral Medium 3.1 vs MiniMax-M2 specifications side by side
SpecificationQwen3 VL 235B A22B InstructAlibaba (Qwen)Mistral Medium 3.1Mistral AIMiniMax-M2MiniMax
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30 (best)$0.40$0.30 (best)
Output$1.55$2.00$1.20 (best)
Cached input———
Blended (3:1)$0.613$0.80$0.525 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 12 providersOfficial Mistral APIOfficial MiniMax (minimax.io) API
Limits
Context window131,072 tokens262,144 tokens (best)204,800 tokens
Max output32,768 tokens262,144 tokens (best)131,072 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoYes
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsOpenProprietaryOpen
API model ID—mistral-medium-2508MiniMax-M2
API providers12113 (best)
ReleasedSep 23, 2025Aug 12, 2025Oct 27, 2025
Knowledge cutoffMar 31, 2025May 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.

  • Qwen3 VL 235B A22B Instruct$6.10
  • Mistral Medium 3.1$8.00
  • MiniMax-M2$5.40
04 — Questions

Which should you choose?

Which is better: Qwen3 VL 235B A22B Instruct, Mistral Medium 3.1 or MiniMax-M2?

Qwen3 VL 235B A22B Instruct is the better all-round choice, scoring 53/100 against Mistral Medium 3.1 (50) and MiniMax-M2 (48). It leads on inputs & features. Mistral Medium 3.1 wins on context window. MiniMax-M2 wins on 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 VL 235B A22B Instruct, Mistral Medium 3.1 or MiniMax-M2?

MiniMax-M2 is cheaper at $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). Qwen3 VL 235B A22B Instruct costs $0.30 input / $1.55 output per million tokens (median across 12 API providers); Mistral Medium 3.1 costs $0.40 input / $2.00 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for MiniMax-M2 versus $0.613 for Qwen3 VL 235B A22B Instruct (1.2× as much) and $0.80 for Mistral Medium 3.1 (1.5× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Qwen3 VL 235B A22B Instruct has not been scored yet, Mistral Medium 3.1 has not been scored yet and MiniMax-M2 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3 VL 235B A22B Instruct, Mistral Medium 3.1 and MiniMax-M2 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?

Mistral Medium 3.1 has the largest context window at 262,144 tokens, against 204,800 for MiniMax-M2 and 131,072 for Qwen3 VL 235B A22B Instruct. Maximum output per response: Qwen3 VL 235B A22B Instruct up to 32,768, Mistral Medium 3.1 up to 262,144, MiniMax-M2 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Qwen3 VL 235B A22B Instruct accepts text and images; Mistral Medium 3.1 accepts text and images; MiniMax-M2 accepts text. Qwen3 VL 235B A22B Instruct handles the widest range of inputs.

Are any of these open source?

Qwen3 VL 235B A22B Instruct and MiniMax-M2 publishes its weights and can be self-hosted; Mistral Medium 3.1 is proprietary.

Which is newer?

MiniMax-M2 is the newest, released Oct 27, 2025. Qwen3 VL 235B A22B Instruct came out Sep 23, 2025; Mistral Medium 3.1 came out Aug 12, 2025. Knowledge cutoff: Qwen3 VL 235B A22B Instruct Mar 31, 2025, Mistral Medium 3.1 May 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons