ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen3.7 Plus vs Qwen3.7 Max vs MiniMax-M3

Too close to call on our weighted score (Qwen3.7 Plus 70, MiniMax-M3 69, Qwen3.7 Max 58). The right pick depends on what you value most.

  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. Alibaba (Qwen)

    Qwen3.7 Max

    Released May 21, 2026

    58/100
    • ECI153.7
    • Price$2.50 / $7.50
    • Context1M
    Full specs Remove Qwen3.7 Max

  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

Too close to call

It is close. Our weighted score puts them within a point (Qwen3.7 Plus 70/100, MiniMax-M3 69/100, Qwen3.7 Max 58/100), so choose by what matters most for your work: Qwen3.7 Max for raw capability, MiniMax-M3 on price and MiniMax-M3 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityQwen3.7 MaxCapabilities Index (ECI): Qwen3.7 Max 153.7 · Qwen3.7 Plus 147.4 · MiniMax-M3 147.0
  • Lowest priceMiniMax-M3MiniMax-M3 $0.525 · Qwen3.7 Plus $0.70 · Qwen3.7 Max $3.75 per 1M tokens (3:1 blend)
  • Longest contextMiniMax-M3MiniMax-M3 1,048,576 · Qwen3.7 Plus 1,000,000 · Qwen3.7 Max 1,000,000 tokens
  • Widest inputsQwen3.7 Plus and MiniMax-M3Qwen3.7 Plus: Text, Images, Video · Qwen3.7 Max: Text · MiniMax-M3: Text, Images, Video
  • Self-hostingMiniMax-M3Publishes downloadable weights
How the score is built
MeasureWeightQwen3.7 PlusQwen3.7 MaxMiniMax-M3
CapabilityCapabilities Index (ECI)50%758374
Price25%572363
Inputs & features15%803570
Context window10%606061
Overall100%70/10058/10069/100
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 Qwen3.7 Max vs MiniMax-M3 specifications side by side
SpecificationQwen3.7 PlusAlibaba (Qwen)Qwen3.7 MaxAlibaba (Qwen)MiniMax-M3MiniMax
Capability
Capabilities Index (ECI)147.4153.7 (best)147.0
ECI rank#61 of 148#37 of 148 (best)#62 of 148
GPQA DiamondGraduate-level science questions87.9%90.9% (best)90.9% (best)
FrontierMath Tiers 1–3Research-level mathematics34.4%64.6% (best)—
OTIS Mock AIME 2024–2025Competition mathematics93.3%95.6% (best)71.1%
SWE-bench VerifiedFixing real GitHub issues—77.3%—
SimpleQA VerifiedShort factual questions—55.8%—
Price per million tokens
Input$0.40$2.50$0.30 (best)
Output$1.60$7.50$1.20 (best)
Cached input$0.04 (best)$0.50$0.06
Blended (3:1)$0.70$3.75$0.525 (best)
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
ImagesYesNoYes
PDFsNoNoNo
AudioNoNoNo
VideoYesNoYes
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryProprietaryOpen
API model IDqwen3.7-plusqwen3.7-maxMiniMax-M3
API providers252642 (best)
ReleasedJun 2, 2026May 21, 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
  • Qwen3.7 Max$40.00
  • MiniMax-M3$5.40
04 — Questions

Which should you choose?

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

It is close. Our weighted score puts them within a point (Qwen3.7 Plus 70/100, MiniMax-M3 69/100, Qwen3.7 Max 58/100), so choose by what matters most for your work: Qwen3.7 Max for raw capability, MiniMax-M3 on price and MiniMax-M3 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

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

MiniMax-M3 is cheaper at $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); Qwen3.7 Max costs $2.50 input / $7.50 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for MiniMax-M3 versus $0.70 for Qwen3.7 Plus (1.3× as much) and $3.75 for Qwen3.7 Max (7.1× as much).

Which scores higher on benchmarks?

Qwen3.7 Max scores higher on the Capabilities Index (ECI): Qwen3.7 Max 153.7 (#37 of 148), Qwen3.7 Plus 147.4 (#61 of 148) and MiniMax-M3 147.0 (#62 of 148). Their confidence ranges do not overlap (151.9–156.0 vs 145.7–148.9), so the gap is a real one. On individual benchmarks: GPQA Diamond — Qwen3.7 Max 90.9%, MiniMax-M3 90.9%, Qwen3.7 Plus 87.9%; OTIS Mock AIME 2024–2025 — Qwen3.7 Max 95.6%, Qwen3.7 Plus 93.3%, MiniMax-M3 71.1%.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3.7 Plus and MiniMax-M3 yet, so there is no like-for-like coding score. On overall capability, Qwen3.7 Max 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 Qwen3.7 Max. Maximum output per response: Qwen3.7 Plus up to 64,000, Qwen3.7 Max 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; Qwen3.7 Max accepts text; MiniMax-M3 accepts text, images and video. Qwen3.7 Plus handles the widest range of inputs.

Are any of these open source?

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

Which is newer?

Qwen3.7 Plus is the newest, released Jun 2, 2026. MiniMax-M3 came out Jun 1, 2026; Qwen3.7 Max came out May 21, 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