ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Qwen3.5 397B-A17B vs Qwen3 Coder Next vs Kimi K2.5

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Alibaba (Qwen)

    Qwen3.5 397B-A17B

    Released Feb 15, 2026

    54/100
    • ECI148.0
    • Price$0.60 / $3.60
    • Context262K
  2. Alibaba (Qwen)

    Qwen3 Coder Next

    Released Feb 3, 2026

    48/100
    • ECI—
    • Price$0.20 / $1.20
    • Context262K
  3. Moonshot AI

    Kimi K2.5

    Released Jan 27, 2026

    52/100
    • ECI148.8
    • Price$0.60 / $3.00
    • Context262K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 397B-A17B 54/100, Kimi K2.5 52/100, Qwen3 Coder Next 48/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceQwen3 Coder NextQwen3 Coder Next $0.45 · Kimi K2.5 $1.20 · Qwen3.5 397B-A17B $1.35 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameQwen3.5 397B-A17B 262,144 · Qwen3 Coder Next 262,144 · Kimi K2.5 262,144 tokens
  • Widest inputsQwen3.5 397B-A17B and Kimi K2.5Qwen3.5 397B-A17B: Text, Images, Video · Qwen3 Coder Next: Text · Kimi K2.5: Text, Images, Video
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightQwen3.5 397B-A17BQwen3 Coder NextKimi K2.5
Price50%426344
Inputs & features30%802570
Context window20%434343
Specs & price only100%54/10048/10052/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

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 Qwen3 Coder Next vs Kimi K2.5 specifications side by side
SpecificationQwen3.5 397B-A17BAlibaba (Qwen)Qwen3 Coder NextAlibaba (Qwen)Kimi K2.5Moonshot AI
Capability
Capabilities Index (ECI)148.0—148.8 (best)
ECI rank#76 of 158—#73 of 158 (best)
GPQA DiamondGraduate-level science questions86.4%—87.6% (best)
FrontierMath Tiers 1–3Research-level mathematics31.2%——
OTIS Mock AIME 2024–2025Competition mathematics88.9%—92.2% (best)
SWE-bench VerifiedFixing real GitHub issues——73.8%
SimpleQA VerifiedShort factual questions——34.3%
Price per million tokens
Input$0.60$0.20 (best)$0.60
Output$3.60$1.20 (best)$3.00
Cached input———
Blended (3:1)$1.35$0.45 (best)$1.20
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Alibaba APIMedian of 17 providersMedian of 36 providers
Limits
Context window262,144 tokens262,144 tokens262,144 tokens
Max output65,536 tokens65,536 tokens262,144 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoNo
AudioNoNoNo
VideoYesNoYes
ReasoningYesNoYes
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsOpenOpenOpen
API model IDqwen3.5-397b-a17b——
API providers36 (best)1836 (best)
ReleasedFeb 15, 2026Feb 3, 2026Jan 27, 2026
Knowledge cutoff—Sep 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
  • Qwen3 Coder Next$4.40
  • Kimi K2.5$12.00
04 — Questions

Which should you choose?

Which is better: Qwen3.5 397B-A17B, Qwen3 Coder Next or Kimi K2.5?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 397B-A17B 54/100, Kimi K2.5 52/100, Qwen3 Coder Next 48/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Qwen3.5 397B-A17B, Qwen3 Coder Next or Kimi K2.5?

Qwen3 Coder Next is cheaper at $0.20 input / $1.20 output per million tokens (median across 17 API providers). Kimi K2.5 costs $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). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Qwen3 Coder Next versus $1.20 for Kimi K2.5 (2.7× as much) and $1.35 for Qwen3.5 397B-A17B (3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Qwen3.5 397B-A17B has an ECI of 148.0, Qwen3 Coder Next has not been scored yet and Kimi K2.5 has an ECI of 148.8.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3.5 397B-A17B and Qwen3 Coder Next yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Qwen3.5 397B-A17B, Qwen3 Coder Next and Kimi K2.5 share the same 262,144-token context window. Maximum output per response: Qwen3.5 397B-A17B up to 65,536, Qwen3 Coder Next up to 65,536, 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; Qwen3 Coder Next accepts text; Kimi K2.5 accepts text, images and video. Qwen3.5 397B-A17B handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights, so you can self-host them.

Which is newer?

Qwen3.5 397B-A17B is the newest, released Feb 15, 2026. Qwen3 Coder Next came out Feb 3, 2026; Kimi K2.5 came out Jan 27, 2026. Knowledge cutoff: Qwen3 Coder Next Sep 2025, Kimi K2.5 Jan 2025.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.