ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen3.7 Plus vs Qwen3.5 Flash vs MiniMax-M3

Qwen3.5 Flash comes out ahead, 75 to 70 and 69 on our weighted score, and it is the cheaper option too.

  1. Alibaba (Qwen)

    Qwen3.7 Plus

    Released Jun 2, 2026

    70/100
    • ECI147.4
    • Price$0.40 / $1.60
    • Context1M
    Full specs Remove Qwen3.7 Plus
  2. Our pick

    Alibaba (Qwen)

    Qwen3.5 Flash

    Released Feb 23, 2026

    75/100
    • ECI144.0
    • Price$0.10 / $0.40
    • Context1M
    Full specs Remove Qwen3.5 Flash

  3. MiniMax

    MiniMax-M3

    Released Jun 1, 2026

    69/100
    • ECI147.0
    • Price$0.30 / $1.20
    • Context1.05M
    Full specs Remove MiniMax-M3
01 — Verdict

Qwen3.5 Flash is our pick

Qwen3.5 Flash is the better all-round choice, scoring 75/100 against Qwen3.7 Plus (70) and MiniMax-M3 (69). It leads on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityQwen3.7 PlusCapabilities Index (ECI): Qwen3.7 Plus 147.4 · MiniMax-M3 147.0 · Qwen3.5 Flash 144.0
  • Lowest priceQwen3.5 FlashQwen3.5 Flash $0.175 · MiniMax-M3 $0.525 · Qwen3.7 Plus $0.70 per 1M tokens (3:1 blend)
  • Longest contextMiniMax-M3MiniMax-M3 1,048,576 · Qwen3.7 Plus 1,000,000 · Qwen3.5 Flash 1,000,000 tokens
  • Widest inputsSame inputsQwen3.7 Plus: Text, Images, Video · Qwen3.5 Flash: Text, Images, Video · MiniMax-M3: Text, Images, Video
  • Self-hostingMiniMax-M3Publishes downloadable weights
How the score is built
MeasureWeightQwen3.7 PlusQwen3.5 FlashMiniMax-M3
CapabilityCapabilities Index (ECI)50%757174
Price25%578663
Inputs & features15%808070
Context window10%606061
Overall100%70/10075/10069/100
02 — Side by side

Every spec in one table

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

Qwen3.7 Plus vs Qwen3.5 Flash vs MiniMax-M3 specifications side by side
SpecificationQwen3.7 PlusAlibaba (Qwen)Qwen3.5 FlashAlibaba (Qwen)MiniMax-M3MiniMax
Capability
Capabilities Index (ECI)147.4 (best)144.0147.0
ECI rank#61 of 148 (best)#82 of 148#62 of 148
GPQA DiamondGraduate-level science questions87.9%82.3%90.9% (best)
FrontierMath Tiers 1–3Research-level mathematics34.4% (best)18.3%—
OTIS Mock AIME 2024–2025Competition mathematics93.3% (best)84.4%71.1%
SimpleQA VerifiedShort factual questions—20.3%—
Price per million tokens
Input$0.40$0.10 (best)$0.30
Output$1.60$0.40 (best)$1.20
Cached input$0.04$0.01 (best)$0.06
Blended (3:1)$0.70$0.175 (best)$0.525
Long-context rateOver 256K: $1.20 / $4.80Same rateOver 512K: $0.60 / $2.40
Price sourceOfficial Alibaba APIOfficial Alibaba APIOfficial MiniMax (minimax.io) API
Limits
Context window1,000,000 tokens1,000,000 tokens1,048,576 tokens (best)
Max output64,000 tokens65,536 tokens512,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioNoNoNo
VideoYesYesYes
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryProprietaryOpen
API model IDqwen3.7-plusqwen3.5-flashMiniMax-M3
API providers25842 (best)
ReleasedJun 2, 2026Feb 23, 2026Jun 1, 2026
Knowledge cutoffApr 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.

  • Qwen3.7 Plus$7.20
  • Qwen3.5 Flash$1.80
  • MiniMax-M3$5.40
04 — Questions

Which should you choose?

Which is better: Qwen3.7 Plus, Qwen3.5 Flash or MiniMax-M3?

Qwen3.5 Flash is the better all-round choice, scoring 75/100 against Qwen3.7 Plus (70) and MiniMax-M3 (69). It leads on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Qwen3.7 Plus, Qwen3.5 Flash or MiniMax-M3?

Qwen3.5 Flash is cheaper at $0.10 input / $0.40 output per million tokens (official Alibaba API price). MiniMax-M3 costs $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price); Qwen3.7 Plus costs $0.40 input / $1.60 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.175 per million tokens for Qwen3.5 Flash versus $0.525 for MiniMax-M3 (3× as much) and $0.70 for Qwen3.7 Plus (4× as much).

Which scores higher on benchmarks?

Qwen3.7 Plus scores higher on the Capabilities Index (ECI): Qwen3.7 Plus 147.4 (#61 of 148), MiniMax-M3 147.0 (#62 of 148) and Qwen3.5 Flash 144.0 (#82 of 148). The confidence ranges of the top two overlap (145.7–148.9 vs 142.7–149.8), so treat the gap as small. On individual benchmarks: GPQA Diamond — MiniMax-M3 90.9%, Qwen3.7 Plus 87.9%, Qwen3.5 Flash 82.3%; OTIS Mock AIME 2024–2025 — Qwen3.7 Plus 93.3%, Qwen3.5 Flash 84.4%, MiniMax-M3 71.1%.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3.7 Plus, Qwen3.5 Flash and MiniMax-M3 yet, so there is no like-for-like coding score. On overall capability, Qwen3.7 Plus 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 1,000,000 for Qwen3.7 Plus and 1,000,000 for Qwen3.5 Flash. Maximum output per response: Qwen3.7 Plus up to 64,000, Qwen3.5 Flash up to 65,536, MiniMax-M3 up to 512,000 tokens.

Which can read images, PDFs, audio or video?

Qwen3.7 Plus accepts text, images and video; Qwen3.5 Flash accepts text, images and video; MiniMax-M3 accepts text, images and video. They handle the same number of input types.

Are any of these open source?

MiniMax-M3 publishes its weights and can be self-hosted; Qwen3.7 Plus and Qwen3.5 Flash is proprietary.

Which is newer?

Qwen3.7 Plus is the newest, released Jun 2, 2026. MiniMax-M3 came out Jun 1, 2026; Qwen3.5 Flash came out Feb 23, 2026. Knowledge cutoff: Qwen3.7 Plus Apr 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