ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen3.7 Plus vs GPT-6 Luna vs MiniMax-M3

GPT-6 Luna comes out ahead, 86 to 78 and 73 on our weighted score, and it is the cheaper option too.

  1. Alibaba (Qwen)

    Qwen3.7 Plus

    Released Jun 2, 2026

    78/100
    • ECI147.4
    • Price$0.40 / $1.60
    • Context1M
    Full specs Remove Qwen3.7 Plus
  2. Our pick

    OpenAI

    GPT-6 Luna

    Released Sep 22, 2026

    86/100
    • ECI—
    • Price$0.10 / $0.50
    • Context1.05M
    Full specs Remove GPT-6 Luna

  3. MiniMax

    MiniMax-M3

    Released Jun 1, 2026

    73/100
    • ECI147.0
    • Price$0.30 / $1.20
    • Context1.05M
    Full specs Remove MiniMax-M3
01 — Verdict

GPT-6 Luna is our pick

GPT-6 Luna is the better all-round choice, scoring 86/100 against Qwen3.7 Plus (78) and MiniMax-M3 (73). It leads on capability and price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because GPT-6 Luna has no Capabilities Index score yet.

  • CapabilityGPT-6 LunaShared benchmarks: GPT-6 Luna 94.7% · Qwen3.7 Plus 90.6% · MiniMax-M3 81.0%
  • Lowest priceGPT-6 LunaGPT-6 Luna $0.20 · MiniMax-M3 $0.525 · Qwen3.7 Plus $0.70 per 1M tokens (3:1 blend)
  • Longest contextGPT-6 Luna and MiniMax-M3GPT-6 Luna 1,050,000 · MiniMax-M3 1,048,576 · Qwen3.7 Plus 1,000,000 tokens
  • Widest inputsSame inputsQwen3.7 Plus: Text, Images, Video · GPT-6 Luna: Text, Images, PDFs · MiniMax-M3: Text, Images, Video
  • Self-hostingMiniMax-M3Publishes downloadable weights
How the score is built
MeasureWeightQwen3.7 PlusGPT-6 LunaMiniMax-M3
CapabilityShared benchmarks50%919581
Price25%578363
Inputs & features15%808070
Context window10%606161
Overall100%78/10086/10073/100
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 GPT-6 Luna vs MiniMax-M3 specifications side by side
SpecificationQwen3.7 PlusAlibaba (Qwen)GPT-6 LunaOpenAIMiniMax-M3MiniMax
Capability
Capabilities Index (ECI)147.4 (best)—147.0
ECI rank#61 of 148 (best)—#62 of 148
GPQA DiamondGraduate-level science questions87.9%90.5%90.9% (best)
FrontierMath Tiers 1–3Research-level mathematics34.4%79.0% (best)—
OTIS Mock AIME 2024–2025Competition mathematics93.3%98.9% (best)71.1%
SimpleQA VerifiedShort factual questions—41.4%—
Price per million tokens
Input$0.40$0.10 (best)$0.30
Output$1.60$0.50 (best)$1.20
Cached input$0.04$0.01 (best)$0.06
Blended (3:1)$0.70$0.20 (best)$0.525
Long-context rateOver 256K: $1.20 / $4.80Over 272K: $0.20 / $0.75Over 512K: $0.60 / $2.40
Price sourceOfficial Alibaba APIOfficial OpenAI APIOfficial MiniMax (minimax.io) API
Limits
Context window1,000,000 tokens1,050,000 tokens (best)1,048,576 tokens
Max output64,000 tokens128,000 tokens512,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesNo
AudioNoNoNo
VideoYesNoYes
ReasoningYesYeslow · medium · high · xhigh · maxYes
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryProprietaryOpen
API model IDqwen3.7-plusgpt-6-lunaMiniMax-M3
API providers252442 (best)
ReleasedJun 2, 2026Sep 22, 2026Jun 1, 2026
Knowledge cutoffApr 2025May 18, 2026—
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
  • GPT-6 Luna$2.00
  • MiniMax-M3$5.40
04 — Questions

Which should you choose?

Which is better: Qwen3.7 Plus, GPT-6 Luna or MiniMax-M3?

GPT-6 Luna is the better all-round choice, scoring 86/100 against Qwen3.7 Plus (78) and MiniMax-M3 (73). It leads on capability and price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because GPT-6 Luna has no Capabilities Index score yet.

Which is cheaper, Qwen3.7 Plus, GPT-6 Luna or MiniMax-M3?

GPT-6 Luna is cheaper at $0.10 input / $0.50 output per million tokens (official OpenAI 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 $0.20 per million tokens for GPT-6 Luna versus $0.525 for MiniMax-M3 (2.6× as much) and $0.70 for Qwen3.7 Plus (3.5× as much).

Which scores higher on benchmarks?

Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): GPT-6 Luna 94.7%, Qwen3.7 Plus 90.6% and MiniMax-M3 81.0%. On individual benchmarks: GPQA Diamond — MiniMax-M3 90.9%, GPT-6 Luna 90.5%, Qwen3.7 Plus 87.9%; OTIS Mock AIME 2024–2025 — GPT-6 Luna 98.9%, 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, GPT-6 Luna and MiniMax-M3 yet, so there is no like-for-like coding score. On overall capability, GPT-6 Luna 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?

GPT-6 Luna and MiniMax-M3 have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for Qwen3.7 Plus. Maximum output per response: Qwen3.7 Plus up to 64,000, GPT-6 Luna up to 128,000, MiniMax-M3 up to 512,000 tokens.

Which can read images, PDFs, audio or video?

Qwen3.7 Plus accepts text, images and video; GPT-6 Luna accepts text, images and PDFs; 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 GPT-6 Luna is proprietary.

Which is newer?

GPT-6 Luna is the newest, released Sep 22, 2026. Qwen3.7 Plus came out Jun 2, 2026; MiniMax-M3 came out Jun 1, 2026. Knowledge cutoff: Qwen3.7 Plus Apr 2025, GPT-6 Luna May 18, 2026.

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