ZMIME
Comparison · 2 models · Updated Oct 4, 2026

MiniMax-M3 vs GPT-6 Luna

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

  1. MiniMax

    MiniMax-M3

    Released Jun 1, 2026

    73/100
    • ECI147.0
    • Price$0.30 / $1.20
    • Context1.05M
    Full specs Remove MiniMax-M3
  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. Add a model

    Make it a three-way comparison.

01 — Verdict

GPT-6 Luna is our pick

GPT-6 Luna is the better all-round choice, scoring 86/100 against MiniMax-M3 (73). It leads on capability, price and inputs & features. 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% · MiniMax-M3 81.0%
  • Lowest priceGPT-6 LunaGPT-6 Luna $0.20 · MiniMax-M3 $0.525 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameGPT-6 Luna 1,050,000 · MiniMax-M3 1,048,576 tokens
  • Widest inputsSame inputsMiniMax-M3: Text, Images, Video · GPT-6 Luna: Text, Images, PDFs
  • Self-hostingMiniMax-M3Publishes downloadable weights
How the score is built
MeasureWeightMiniMax-M3GPT-6 Luna
CapabilityShared benchmarks50%8195
Price25%6383
Inputs & features15%7080
Context window10%6161
Overall100%73/10086/100
02 — Side by side

Every spec in one table

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

MiniMax-M3 vs GPT-6 Luna specifications side by side
SpecificationMiniMax-M3MiniMaxGPT-6 LunaOpenAI
Capability
Capabilities Index (ECI)147.0—
ECI rank#62 of 148—
GPQA DiamondGraduate-level science questions90.9% (best)90.5%
FrontierMath Tiers 1–3Research-level mathematics—79.0%
OTIS Mock AIME 2024–2025Competition mathematics71.1%98.9% (best)
SimpleQA VerifiedShort factual questions—41.4%
Price per million tokens
Input$0.30$0.10 (best)
Output$1.20$0.50 (best)
Cached input$0.06$0.01 (best)
Blended (3:1)$0.525$0.20 (best)
Long-context rateOver 512K: $0.60 / $2.40Over 272K: $0.20 / $0.75
Price sourceOfficial MiniMax (minimax.io) APIOfficial OpenAI API
Limits
Context window1,048,576 tokens1,050,000 tokens (best)
Max output512,000 tokens (best)128,000 tokens
Inputs and features
TextYesYes
ImagesYesYes
PDFsNoYes
AudioNoNo
VideoYesNo
ReasoningYesYeslow · medium · high · xhigh · max
Tool callingYesYes
Structured outputNoYes
Availability
WeightsOpenProprietary
API model IDMiniMax-M3gpt-6-luna
API providers42 (best)24
ReleasedJun 1, 2026Sep 22, 2026
Knowledge cutoff—May 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.

  • MiniMax-M3$5.40
  • GPT-6 Luna$2.00
04 — Questions

Which should you choose?

Which is better: MiniMax-M3 or GPT-6 Luna?

GPT-6 Luna is the better all-round choice, scoring 86/100 against MiniMax-M3 (73). It leads on capability, price and inputs & features. 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, MiniMax-M3 or GPT-6 Luna?

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). 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).

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% and MiniMax-M3 81.0%. On individual benchmarks: GPQA Diamond — MiniMax-M3 90.9%, GPT-6 Luna 90.5%; OTIS Mock AIME 2024–2025 — GPT-6 Luna 98.9%, MiniMax-M3 71.1%.

Which is better for coding?

There are no published SWE-bench Verified results for MiniMax-M3 and GPT-6 Luna 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. Both support tool calling for agent workflows.

Which has the bigger context window?

Their context windows are effectively the same size: MiniMax-M3 1,048,576 and GPT-6 Luna 1,050,000 tokens. Maximum output per response: MiniMax-M3 up to 512,000, GPT-6 Luna up to 128,000 tokens.

Which can read images, PDFs, audio or video?

MiniMax-M3 accepts text, images and video; GPT-6 Luna accepts text, images and PDFs. They handle the same number of input types.

Are any of these open source?

MiniMax-M3 publishes its weights and can be self-hosted; GPT-6 Luna is proprietary.

Which is newer?

GPT-6 Luna is the newest, released Sep 22, 2026. MiniMax-M3 came out Jun 1, 2026. Knowledge cutoff: 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