ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Qwen3.5 397B-A17B vs GPT-5.4 mini vs Kimi K2.5

Too close to call on our weighted score (Qwen3.5 397B-A17B 64, Kimi K2.5 64, GPT-5.4 mini 63). The right pick depends on what you value most.

Price in rating: Included · Exclude price

  1. Alibaba (Qwen)

    Qwen3.5 397B-A17B

    Released Feb 15, 2026

    64/100
    • ECI148.0
    • Price$0.60 / $3.60
    • Context262K
  2. OpenAI

    GPT-5.4 mini

    Released Mar 17, 2026

    63/100
    • ECI149.4
    • Price$0.75 / $4.50
    • Context400K
  3. Moonshot AI

    Kimi K2.5

    Released Jan 27, 2026

    64/100
    • ECI148.8
    • Price$0.60 / $3.00
    • Context262K
01 — Verdict

Too close to call

It is close. Our weighted score puts them within a point (Qwen3.5 397B-A17B 64/100, Kimi K2.5 64/100, GPT-5.4 mini 63/100), so choose by what matters most for your work: GPT-5.4 mini for raw capability and Kimi K2.5 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGPT-5.4 miniCapabilities Index (ECI): GPT-5.4 mini 149.4 · Kimi K2.5 148.8 · Qwen3.5 397B-A17B 148.0
  • Lowest priceKimi K2.5Kimi K2.5 $1.20 · Qwen3.5 397B-A17B $1.35 · GPT-5.4 mini $1.69 per 1M tokens (3:1 blend)
  • Longest contextGPT-5.4 miniGPT-5.4 mini 400,000 · Qwen3.5 397B-A17B 262,144 · Kimi K2.5 262,144 tokens
  • Widest inputsQwen3.5 397B-A17B and Kimi K2.5Qwen3.5 397B-A17B: Text, Images, Video · GPT-5.4 mini: Text, Images · Kimi K2.5: Text, Images, Video
  • Self-hostingQwen3.5 397B-A17B and Kimi K2.5Publishes downloadable weights
How the score is built
MeasureWeightQwen3.5 397B-A17BGPT-5.4 miniKimi K2.5
CapabilityCapabilities Index (ECI)50%757776
Price25%423744
Inputs & features15%807070
Context window10%435043
Overall100%64/10063/10064/100
02 — Side by side

Every spec in one table

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

Qwen3.5 397B-A17B vs GPT-5.4 mini vs Kimi K2.5 specifications side by side
SpecificationQwen3.5 397B-A17BAlibaba (Qwen)GPT-5.4 miniOpenAIKimi K2.5Moonshot AI
Capability
Capabilities Index (ECI)148.0149.4 (best)148.8
ECI rank#76 of 158#71 of 158 (best)#73 of 158
GPQA DiamondGraduate-level science questions86.4%86.9%87.6% (best)
FrontierMath Tiers 1–3Research-level mathematics31.2%51.2% (best)—
OTIS Mock AIME 2024–2025Competition mathematics88.9%88.9%92.2% (best)
SWE-bench VerifiedFixing real GitHub issues——73.8%
SimpleQA VerifiedShort factual questions—29.4%34.3% (best)
Price per million tokens
Input$0.60 (best)$0.75$0.60 (best)
Output$3.60$4.50$3.00 (best)
Cached input—$0.075—
Blended (3:1)$1.35$1.69$1.20 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Alibaba APIOfficial OpenAI APIMedian of 36 providers
Limits
Context window262,144 tokens400,000 tokens (best)262,144 tokens
Max output65,536 tokens128,000 tokens262,144 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioNoNoNo
VideoYesNoYes
ReasoningYesYeslow · medium · high · xhighYes
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsOpenProprietaryOpen
API model IDqwen3.5-397b-a17bgpt-5.4-mini—
API providers3642 (best)36
ReleasedFeb 15, 2026Mar 17, 2026Jan 27, 2026
Knowledge cutoff—Aug 31, 2025Jan 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.

  • Qwen3.5 397B-A17B$13.20
  • GPT-5.4 mini$16.50
  • Kimi K2.5$12.00
04 — Questions

Which should you choose?

Which is better: Qwen3.5 397B-A17B, GPT-5.4 mini or Kimi K2.5?

It is close. Our weighted score puts them within a point (Qwen3.5 397B-A17B 64/100, Kimi K2.5 64/100, GPT-5.4 mini 63/100), so choose by what matters most for your work: GPT-5.4 mini for raw capability and Kimi K2.5 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Qwen3.5 397B-A17B, GPT-5.4 mini or Kimi K2.5?

Kimi K2.5 is cheaper at $0.60 input / $3.00 output per million tokens (median across 36 API providers). Qwen3.5 397B-A17B costs $0.60 input / $3.60 output per million tokens (official Alibaba API price); GPT-5.4 mini costs $0.75 input / $4.50 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $1.20 per million tokens for Kimi K2.5 versus $1.35 for Qwen3.5 397B-A17B (1.1× as much) and $1.69 for GPT-5.4 mini (1.4× as much).

Which scores higher on benchmarks?

GPT-5.4 mini scores higher on the Capabilities Index (ECI): GPT-5.4 mini 149.4 (#71 of 158), Kimi K2.5 148.8 (#73 of 158) and Qwen3.5 397B-A17B 148.0 (#76 of 158). The confidence ranges of the top two overlap (147.7–151.1 vs 147.3–150.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — Kimi K2.5 87.6%, GPT-5.4 mini 86.9%, Qwen3.5 397B-A17B 86.4%; OTIS Mock AIME 2024–2025 — Kimi K2.5 92.2%, Qwen3.5 397B-A17B 88.9%, GPT-5.4 mini 88.9%.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3.5 397B-A17B and GPT-5.4 mini yet, so there is no like-for-like coding score. On overall capability, GPT-5.4 mini 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-5.4 mini has the largest context window at 400,000 tokens, against 262,144 for Qwen3.5 397B-A17B and 262,144 for Kimi K2.5. Maximum output per response: Qwen3.5 397B-A17B up to 65,536, GPT-5.4 mini up to 128,000, Kimi K2.5 up to 262,144 tokens.

Which can read images, PDFs, audio or video?

Qwen3.5 397B-A17B accepts text, images and video; GPT-5.4 mini accepts text and images; Kimi K2.5 accepts text, images and video. Qwen3.5 397B-A17B handles the widest range of inputs.

Are any of these open source?

Qwen3.5 397B-A17B and Kimi K2.5 publishes its weights and can be self-hosted; GPT-5.4 mini is proprietary.

Which is newer?

GPT-5.4 mini is the newest, released Mar 17, 2026. Qwen3.5 397B-A17B came out Feb 15, 2026; Kimi K2.5 came out Jan 27, 2026. Knowledge cutoff: GPT-5.4 mini Aug 31, 2025, Kimi K2.5 Jan 2025.

How do you decide the winner?

This rating uses 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 Nov 18, 2026.