ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Kimi K2.5 vs Qwen3.5 397B-A17B vs Qwen3.6 Plus

Qwen3.6 Plus comes out ahead, 75 to 72 and 70 on our weighted score, and it is the cheaper option too.

Price in rating: Excluded · Include price

  1. Moonshot AI

    Kimi K2.5

    Released Jan 27, 2026

    70/100
    • ECI148.8
    • Price$0.60 / $3.00
    • Context262K
  2. Alibaba (Qwen)

    Qwen3.5 397B-A17B

    Released Feb 15, 2026

    72/100
    • ECI148.0
    • Price$0.60 / $3.60
    • Context262K
  3. Our pick

    Alibaba (Qwen)

    Qwen3.6 Plus

    Released Apr 2, 2026

    75/100
    • ECI148.9
    • Price$0.50 / $3.00
    • Context1M
01 — Verdict

Qwen3.6 Plus is our pick

Qwen3.6 Plus is the better all-round choice, scoring 75/100 against Qwen3.5 397B-A17B (72) and Kimi K2.5 (70). It leads on context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityQwen3.6 PlusCapabilities Index (ECI): Qwen3.6 Plus 148.9 · Kimi K2.5 148.8 · Qwen3.5 397B-A17B 148.0
  • Lowest priceQwen3.6 PlusQwen3.6 Plus $1.13 · Kimi K2.5 $1.20 · Qwen3.5 397B-A17B $1.35 per 1M tokens (3:1 blend)
  • Longest contextQwen3.6 PlusQwen3.6 Plus 1,000,000 · Kimi K2.5 262,144 · Qwen3.5 397B-A17B 262,144 tokens
  • Widest inputsSame inputsKimi K2.5: Text, Images, Video · Qwen3.5 397B-A17B: Text, Images, Video · Qwen3.6 Plus: Text, Images, Video
  • Self-hostingKimi K2.5 and Qwen3.5 397B-A17BPublishes downloadable weights
How the score is built
MeasureWeightKimi K2.5Qwen3.5 397B-A17BQwen3.6 Plus
CapabilityCapabilities Index (ECI)67%767576
Inputs & features20%708080
Context window13%434364
Overall100%70/10072/10075/100
02 — Side by side

Every spec in one table

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

Kimi K2.5 vs Qwen3.5 397B-A17B vs Qwen3.6 Plus specifications side by side
SpecificationKimi K2.5Moonshot AIQwen3.5 397B-A17BAlibaba (Qwen)Qwen3.6 PlusAlibaba (Qwen)
Capability
Capabilities Index (ECI)148.8148.0148.9 (best)
ECI rank#73 of 158#76 of 158#72 of 158 (best)
GPQA DiamondGraduate-level science questions87.6%86.4%88.4% (best)
FrontierMath Tiers 1–3Research-level mathematics—31.2%38.3% (best)
OTIS Mock AIME 2024–2025Competition mathematics92.2%88.9%93.3% (best)
SWE-bench VerifiedFixing real GitHub issues73.8% (best)—57.9%
SimpleQA VerifiedShort factual questions34.3%—44.1% (best)
Price per million tokens
Input$0.60$0.60$0.50 (best)
Output$3.00 (best)$3.60$3.00 (best)
Cached input——$0.05
Blended (3:1)$1.20$1.35$1.13 (best)
Long-context rateSame rateSame rateOver 256K: $2.00 / $6.00
Price sourceMedian of 36 providersOfficial Alibaba APIOfficial Alibaba API
Limits
Context window262,144 tokens262,144 tokens1,000,000 tokens (best)
Max output262,144 tokens (best)65,536 tokens65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioNoNoNo
VideoYesYesYes
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoYesYes
Availability
WeightsOpenOpenProprietary
API model ID—qwen3.5-397b-a17bqwen3.6-plus
API providers36 (best)36 (best)23
ReleasedJan 27, 2026Feb 15, 2026Apr 2, 2026
Knowledge cutoffJan 2025—Apr 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.

  • Kimi K2.5$12.00
  • Qwen3.5 397B-A17B$13.20
  • Qwen3.6 Plus$11.00
04 — Questions

Which should you choose?

Which is better: Kimi K2.5, Qwen3.5 397B-A17B or Qwen3.6 Plus?

Qwen3.6 Plus is the better all-round choice, scoring 75/100 against Qwen3.5 397B-A17B (72) and Kimi K2.5 (70). It leads on context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, Kimi K2.5, Qwen3.5 397B-A17B or Qwen3.6 Plus?

Qwen3.6 Plus is cheaper at $0.50 input / $3.00 output per million tokens (official Alibaba API price). 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 $1.13 per million tokens for Qwen3.6 Plus versus $1.20 for Kimi K2.5 (1.1× as much) and $1.35 for Qwen3.5 397B-A17B (1.2× as much).

Which scores higher on benchmarks?

Qwen3.6 Plus scores higher on the Capabilities Index (ECI): Qwen3.6 Plus 148.9 (#72 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 (147.0–150.9 vs 147.3–150.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — Qwen3.6 Plus 88.4%, Kimi K2.5 87.6%, Qwen3.5 397B-A17B 86.4%; OTIS Mock AIME 2024–2025 — Qwen3.6 Plus 93.3%, Kimi K2.5 92.2%, Qwen3.5 397B-A17B 88.9%.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3.5 397B-A17B yet, so there is no like-for-like coding score. On overall capability, Qwen3.6 Plus 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?

Qwen3.6 Plus has the largest context window at 1,000,000 tokens, against 262,144 for Kimi K2.5 and 262,144 for Qwen3.5 397B-A17B. Maximum output per response: Kimi K2.5 up to 262,144, Qwen3.5 397B-A17B up to 65,536, Qwen3.6 Plus up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Kimi K2.5 accepts text, images and video; Qwen3.5 397B-A17B accepts text, images and video; Qwen3.6 Plus accepts text, images and video. They handle the same number of input types.

Are any of these open source?

Kimi K2.5 and Qwen3.5 397B-A17B publishes its weights and can be self-hosted; Qwen3.6 Plus is proprietary.

Which is newer?

Qwen3.6 Plus is the newest, released Apr 2, 2026. Qwen3.5 397B-A17B came out Feb 15, 2026; Kimi K2.5 came out Jan 27, 2026. Knowledge cutoff: Kimi K2.5 Jan 2025, Qwen3.6 Plus Apr 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.