ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Qwen3 235B-A22B Thinking 2507 vs MiniMax-M3 vs Kimi K2 Instruct

MiniMax-M3 comes out ahead, 70 to 57 and 53 on our weighted score, and it is the cheaper option too.

Price in rating: Included · Exclude price

  1. Alibaba (Qwen)

    Qwen3 235B-A22B Thinking 2507

    Released Jul 25, 2025

    57/100
    • ECI143.3
    • Price$0.30 / $2.90
    • Context262K
  2. Our pick

    MiniMax

    MiniMax-M3

    Released Jun 1, 2026

    70/100
    • ECI147.9
    • Price$0.30 / $1.20
    • Context1.05M
  3. Moonshot AI

    Kimi K2 Instruct

    Released Jul 11, 2025

    53/100
    • ECI141.3
    • Price$0.57 / $2.30
    • Context131K
01 — Verdict

MiniMax-M3 is our pick

MiniMax-M3 is the better all-round choice, scoring 70/100 against Qwen3 235B-A22B Thinking 2507 (57) and Kimi K2 Instruct (53). It leads on capability, price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityMiniMax-M3Capabilities Index (ECI): MiniMax-M3 147.9 · Qwen3 235B-A22B Thinking 2507 143.3 · Kimi K2 Instruct 141.3
  • Lowest priceMiniMax-M3MiniMax-M3 $0.525 · Qwen3 235B-A22B Thinking 2507 $0.95 · Kimi K2 Instruct $1.00 per 1M tokens (3:1 blend)
  • Longest contextMiniMax-M3MiniMax-M3 1,048,576 · Qwen3 235B-A22B Thinking 2507 262,144 · Kimi K2 Instruct 131,072 tokens
  • Widest inputsMiniMax-M3Qwen3 235B-A22B Thinking 2507: Text · MiniMax-M3: Text, Images, Video · Kimi K2 Instruct: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightQwen3 235B-A22B Thinking 2507MiniMax-M3Kimi K2 Instruct
CapabilityCapabilities Index (ECI)50%717569
Price25%496048
Inputs & features15%357025
Context window10%436532
Overall100%57/10070/10053/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Qwen3 235B-A22B Thinking 2507 vs MiniMax-M3 vs Kimi K2 Instruct specifications side by side
SpecificationQwen3 235B-A22B Thinking 2507Alibaba (Qwen)MiniMax-M3MiniMaxKimi K2 InstructMoonshot AI
Capability
Capabilities Index (ECI)143.3147.9 (best)141.3
ECI rank#100 of 158#77 of 158 (best)#108 of 158
GPQA DiamondGraduate-level science questions80.1%90.9% (best)—
OTIS Mock AIME 2024–2025Competition mathematics86.7% (best)71.1%—
SimpleQA VerifiedShort factual questions40.4%——
Price per million tokens
Input$0.30 (best)$0.30 (best)$0.57
Output$2.90$1.20 (best)$2.30
Cached input—$0.06—
Blended (3:1)$0.95$0.525 (best)$1.00
Long-context rateSame rateOver 512K: $0.60 / $2.40Same rate
Price sourceMedian of 11 providersOfficial MiniMax (minimax.io) APIMedian of 11 providers
Limits
Context window262,144 tokens1,048,576 tokens (best)131,072 tokens
Max output81,920 tokens512,000 tokens (best)32,768 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoYesNo
ReasoningYesYesNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenApache 2.0OpenOpenModified MIT
API model ID—MiniMax-M3—
API providers1252 (best)11
ReleasedJul 25, 2025Jun 1, 2026Jul 11, 2025
Knowledge cutoff———
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 235B-A22B Thinking 2507$8.80
  • MiniMax-M3$5.40
  • Kimi K2 Instruct$10.30
04 — Questions

Which should you choose?

Which is better: Qwen3 235B-A22B Thinking 2507, MiniMax-M3 or Kimi K2 Instruct?

MiniMax-M3 is the better all-round choice, scoring 70/100 against Qwen3 235B-A22B Thinking 2507 (57) and Kimi K2 Instruct (53). It leads on capability, price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Qwen3 235B-A22B Thinking 2507, MiniMax-M3 or Kimi K2 Instruct?

MiniMax-M3 is cheaper at $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). Qwen3 235B-A22B Thinking 2507 costs $0.30 input / $2.90 output per million tokens (median across 11 API providers); Kimi K2 Instruct costs $0.57 input / $2.30 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for MiniMax-M3 versus $0.95 for Qwen3 235B-A22B Thinking 2507 (1.8× as much) and $1.00 for Kimi K2 Instruct (1.9× as much).

Which scores higher on benchmarks?

MiniMax-M3 scores higher on the Capabilities Index (ECI): MiniMax-M3 147.9 (#77 of 158), Qwen3 235B-A22B Thinking 2507 143.3 (#100 of 158) and Kimi K2 Instruct 141.3 (#108 of 158). Their confidence ranges do not overlap (145.8–150.0 vs 141.4–145.1), so the gap is a real one.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3 235B-A22B Thinking 2507, MiniMax-M3 and Kimi K2 Instruct yet, so there is no like-for-like coding score. On overall capability, MiniMax-M3 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Which has the bigger context window?

MiniMax-M3 has the largest context window at 1,048,576 tokens, against 262,144 for Qwen3 235B-A22B Thinking 2507 and 131,072 for Kimi K2 Instruct. Maximum output per response: Qwen3 235B-A22B Thinking 2507 up to 81,920, MiniMax-M3 up to 512,000, Kimi K2 Instruct up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Qwen3 235B-A22B Thinking 2507 accepts text; MiniMax-M3 accepts text, images and video; Kimi K2 Instruct accepts text. MiniMax-M3 handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (Apache 2.0 and Modified MIT), so you can self-host them.

Which is newer?

MiniMax-M3 is the newest, released Jun 1, 2026. Qwen3 235B-A22B Thinking 2507 came out Jul 25, 2025; Kimi K2 Instruct came out Jul 11, 2025.

How do you decide the winner?

This rating uses 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 18, 2026.