ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek V3.2 vs MiniMax-M3 vs Qwen3.7 Plus

Too close to call on our weighted score (Qwen3.7 Plus 75, MiniMax-M3 73, DeepSeek V3.2 60). The right pick depends on what you value most.

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek V3.2

    Released Dec 1, 2025

    60/100
    • ECI146.3
    • Price$0.28 / $0.42
    • Context128K
  2. MiniMax

    MiniMax-M3

    Released Jun 1, 2026

    73/100
    • ECI147.9
    • Price$0.30 / $1.20
    • Context1.05M
  3. Alibaba (Qwen)

    Qwen3.7 Plus

    Released Jun 2, 2026

    75/100
    • ECI148.0
    • Price$0.40 / $1.60
    • Context1M
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 2 points (Qwen3.7 Plus 75/100, MiniMax-M3 73/100, DeepSeek V3.2 60/100), so choose by what matters most for your work: Qwen3.7 Plus for raw capability, DeepSeek V3.2 on price and MiniMax-M3 for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityQwen3.7 PlusCapabilities Index (ECI): Qwen3.7 Plus 148.0 · MiniMax-M3 147.9 · DeepSeek V3.2 146.3
  • Lowest priceDeepSeek V3.2DeepSeek V3.2 $0.315 · 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 · DeepSeek V3.2 128,000 tokens
  • Widest inputsMiniMax-M3 and Qwen3.7 PlusDeepSeek V3.2: Text · MiniMax-M3: Text, Images, Video · Qwen3.7 Plus: Text, Images, Video
  • Self-hostingDeepSeek V3.2 and MiniMax-M3Publishes downloadable weights (MIT License)
How the score is built
MeasureWeightDeepSeek V3.2MiniMax-M3Qwen3.7 Plus
CapabilityCapabilities Index (ECI)67%747575
Inputs & features20%357080
Context window13%326564
Overall100%60/10073/10075/100
02 — Side by side

Every spec in one table

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

DeepSeek V3.2 vs MiniMax-M3 vs Qwen3.7 Plus specifications side by side
SpecificationDeepSeek V3.2DeepSeekMiniMax-M3MiniMaxQwen3.7 PlusAlibaba (Qwen)
Capability
Capabilities Index (ECI)146.3147.9148.0 (best)
ECI rank#87 of 158#77 of 158#75 of 158 (best)
GPQA DiamondGraduate-level science questions83.4%90.9% (best)87.9%
FrontierMath Tiers 1–3Research-level mathematics——34.4%
OTIS Mock AIME 2024–2025Competition mathematics87.8%71.1%93.3% (best)
Price per million tokens
Input$0.28 (best)$0.30$0.40
Output$0.42 (best)$1.20$1.60
Cached input—$0.06 (best)$0.08
Blended (3:1)$0.315 (best)$0.525$0.70
Long-context rateSame rateOver 512K: $0.60 / $2.40Over 256K: $1.20 / $4.80
Price sourceMedian of 30 providersOfficial MiniMax (minimax.io) APIOfficial Alibaba API
Limits
Context window128,000 tokens1,048,576 tokens (best)1,000,000 tokens
Max output64,000 tokens512,000 tokens (best)64,000 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoYesYes
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenMIT LicenseOpenProprietary
API model ID—MiniMax-M3qwen3.7-plus
API providers3052 (best)28
ReleasedDec 1, 2025Jun 1, 2026Jun 2, 2026
Knowledge cutoffJul 2024—Apr 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.

  • DeepSeek V3.2$3.64
  • MiniMax-M3$5.40
  • Qwen3.7 Plus$7.20
04 — Questions

Which should you choose?

Which is better: DeepSeek V3.2, MiniMax-M3 or Qwen3.7 Plus?

It is close. Our weighted score puts them within 2 points (Qwen3.7 Plus 75/100, MiniMax-M3 73/100, DeepSeek V3.2 60/100), so choose by what matters most for your work: Qwen3.7 Plus for raw capability, DeepSeek V3.2 on price and MiniMax-M3 for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, DeepSeek V3.2, MiniMax-M3 or Qwen3.7 Plus?

DeepSeek V3.2 is cheaper at $0.28 input / $0.42 output per million tokens (median across 30 API providers). 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 $0.315 per million tokens for DeepSeek V3.2 versus $0.525 for MiniMax-M3 (1.7× as much) and $0.70 for Qwen3.7 Plus (2.2× as much).

Which scores higher on benchmarks?

Qwen3.7 Plus scores higher on the Capabilities Index (ECI): Qwen3.7 Plus 148.0 (#75 of 158), MiniMax-M3 147.9 (#77 of 158) and DeepSeek V3.2 146.3 (#87 of 158). The confidence ranges of the top two overlap (145.9–150.0 vs 145.8–150.0), so treat the gap as small. On individual benchmarks: GPQA Diamond — MiniMax-M3 90.9%, Qwen3.7 Plus 87.9%, DeepSeek V3.2 83.4%; OTIS Mock AIME 2024–2025 — Qwen3.7 Plus 93.3%, DeepSeek V3.2 87.8%, MiniMax-M3 71.1%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek V3.2, MiniMax-M3 and Qwen3.7 Plus 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 128,000 for DeepSeek V3.2. Maximum output per response: DeepSeek V3.2 up to 64,000, MiniMax-M3 up to 512,000, Qwen3.7 Plus up to 64,000 tokens.

Which can read images, PDFs, audio or video?

DeepSeek V3.2 accepts text; MiniMax-M3 accepts text, images and video; Qwen3.7 Plus accepts text, images and video. MiniMax-M3 handles the widest range of inputs.

Are any of these open source?

DeepSeek V3.2 and MiniMax-M3 publishes its weights (MIT License) and can be self-hosted; Qwen3.7 Plus is proprietary.

Which is newer?

Qwen3.7 Plus is the newest, released Jun 2, 2026. MiniMax-M3 came out Jun 1, 2026; DeepSeek V3.2 came out Dec 1, 2025. Knowledge cutoff: DeepSeek V3.2 Jul 2024, Qwen3.7 Plus Apr 2025.

How do you decide the winner?

This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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.