ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-5.4 nano vs MiniMax-M3 vs Qwen3.5 9B

MiniMax-M3 comes out ahead, 73 to 70 and 65 on our weighted score, though Qwen3.5 9B is 4.3× cheaper per token.

Price in rating: Excluded · Include price

  1. OpenAI

    GPT-5.4 nano

    Released Mar 17, 2026

    70/100
    • ECI146.3
    • Price$0.20 / $1.25
    • Context400K
  2. Our pick

    MiniMax

    MiniMax-M3

    Released Jun 1, 2026

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

    Qwen3.5 9B

    Released Feb 23, 2026

    65/100
    • ECI139.5
    • Price$0.10 / $0.19
    • Context262K
01 — Verdict

MiniMax-M3 is our pick

MiniMax-M3 is the better all-round choice, scoring 73/100 against GPT-5.4 nano (70) and Qwen3.5 9B (65). It leads on context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityMiniMax-M3Capabilities Index (ECI): MiniMax-M3 147.9 · GPT-5.4 nano 146.3 · Qwen3.5 9B 139.5
  • Lowest priceQwen3.5 9BQwen3.5 9B $0.122 · GPT-5.4 nano $0.463 · MiniMax-M3 $0.525 per 1M tokens (3:1 blend)
  • Longest contextMiniMax-M3MiniMax-M3 1,048,576 · GPT-5.4 nano 400,000 · Qwen3.5 9B 262,144 tokens
  • Widest inputsMiniMax-M3 and Qwen3.5 9BGPT-5.4 nano: Text, Images · MiniMax-M3: Text, Images, Video · Qwen3.5 9B: Text, Images, Video
  • Self-hostingMiniMax-M3 and Qwen3.5 9BPublishes downloadable weights
How the score is built
MeasureWeightGPT-5.4 nanoMiniMax-M3Qwen3.5 9B
CapabilityCapabilities Index (ECI)67%747567
Inputs & features20%707070
Context window13%506543
Overall100%70/10073/10065/100
02 — Side by side

Every spec in one table

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

GPT-5.4 nano vs MiniMax-M3 vs Qwen3.5 9B specifications side by side
SpecificationGPT-5.4 nanoOpenAIMiniMax-M3MiniMaxQwen3.5 9BAlibaba (Qwen)
Capability
Capabilities Index (ECI)146.3147.9 (best)139.5
ECI rank#86 of 158#77 of 158 (best)#116 of 158
GPQA DiamondGraduate-level science questions78.5%90.9% (best)79.0%
FrontierMath Tiers 1–3Research-level mathematics44.9%——
OTIS Mock AIME 2024–2025Competition mathematics87.8% (best)71.1%61.7%
SimpleQA VerifiedShort factual questions11.7%——
Price per million tokens
Input$0.20$0.30$0.10 (best)
Output$1.25$1.20$0.19 (best)
Cached input$0.02 (best)$0.06—
Blended (3:1)$0.463$0.525$0.122 (best)
Long-context rateSame rateOver 512K: $0.60 / $2.40Same rate
Price sourceOfficial OpenAI APIOfficial MiniMax (minimax.io) APIMedian of 20 providers
Limits
Context window400,000 tokens1,048,576 tokens (best)262,144 tokens
Max output128,000 tokens512,000 tokens (best)65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoYesYes
ReasoningYeslow · medium · high · xhighYesYes
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenOpen
API model IDgpt-5.4-nanoMiniMax-M3—
API providers3652 (best)22
ReleasedMar 17, 2026Jun 1, 2026Feb 23, 2026
Knowledge cutoffAug 31, 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.

  • GPT-5.4 nano$4.50
  • MiniMax-M3$5.40
  • Qwen3.5 9B$1.38
04 — Questions

Which should you choose?

Which is better: GPT-5.4 nano, MiniMax-M3 or Qwen3.5 9B?

MiniMax-M3 is the better all-round choice, scoring 73/100 against GPT-5.4 nano (70) and Qwen3.5 9B (65). It leads on context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, GPT-5.4 nano, MiniMax-M3 or Qwen3.5 9B?

Qwen3.5 9B is cheaper at $0.10 input / $0.19 output per million tokens (median across 20 API providers). GPT-5.4 nano costs $0.20 input / $1.25 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 $0.122 per million tokens for Qwen3.5 9B versus $0.463 for GPT-5.4 nano (3.8× as much) and $0.525 for MiniMax-M3 (4.3× as much).

Which scores higher on benchmarks?

MiniMax-M3 scores higher on the Capabilities Index (ECI): MiniMax-M3 147.9 (#77 of 158), GPT-5.4 nano 146.3 (#86 of 158) and Qwen3.5 9B 139.5 (#116 of 158). The confidence ranges of the top two overlap (145.8–150.0 vs 144.7–148.0), so treat the gap as small. On individual benchmarks: GPQA Diamond — MiniMax-M3 90.9%, Qwen3.5 9B 79.0%, GPT-5.4 nano 78.5%; OTIS Mock AIME 2024–2025 — GPT-5.4 nano 87.8%, MiniMax-M3 71.1%, Qwen3.5 9B 61.7%.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-5.4 nano, MiniMax-M3 and Qwen3.5 9B yet, so there is no like-for-like coding score. On overall capability, MiniMax-M3 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 400,000 for GPT-5.4 nano and 262,144 for Qwen3.5 9B. Maximum output per response: GPT-5.4 nano up to 128,000, MiniMax-M3 up to 512,000, Qwen3.5 9B up to 65,536 tokens.

Which can read images, PDFs, audio or video?

GPT-5.4 nano accepts text and images; MiniMax-M3 accepts text, images and video; Qwen3.5 9B accepts text, images and video. MiniMax-M3 handles the widest range of inputs.

Are any of these open source?

MiniMax-M3 and Qwen3.5 9B publishes its weights and can be self-hosted; GPT-5.4 nano is proprietary.

Which is newer?

MiniMax-M3 is the newest, released Jun 1, 2026. GPT-5.4 nano came out Mar 17, 2026; Qwen3.5 9B came out Feb 23, 2026. Knowledge cutoff: GPT-5.4 nano Aug 31, 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.