ZMIME
Comparison · 3 models · Updated Nov 22, 2026

Kimi K2.5 vs Claude Opus 4.1 vs Qwen3.5 397B-A17B

Too close to call on our weighted score (Kimi K2.5 63, Qwen3.5 397B-A17B 62, Claude Opus 4.1 47). The right pick depends on what you value most.Too close to call on our weighted score (Kimi K2.5 71, Qwen3.5 397B-A17B 70, Claude Opus 4.1 67). The right pick depends on what you value most.

  1. Moonshot AI

    Kimi K2.5

    Released Jan 27, 2026

    63/100
    • ECI148.8
    • Price$0.60 / $3.00
    • Context262K
  2. Anthropic

    Claude Opus 4.1

    Released Aug 5, 2025

    47/100
    • ECI144.8
    • Price$15.00 / $75.00
    • Context200K
  3. Alibaba (Qwen)

    Qwen3.5 397B-A17B

    Released Feb 15, 2026

    62/100
    • ECI148.0
    • Price$0.60 / $3.60
    • Context262K
  4. Moonshot AI

    Kimi K2.5

    Released Jan 27, 2026

    71/100
    • ECI148.8
    • Price$0.60 / $3.00
    • Context262K
  5. Anthropic

    Claude Opus 4.1

    Released Aug 5, 2025

    67/100
    • ECI144.8
    • Price$15.00 / $75.00
    • Context200K
  6. Alibaba (Qwen)

    Qwen3.5 397B-A17B

    Released Feb 15, 2026

    70/100
    • ECI148.0
    • Price$0.60 / $3.60
    • Context262K
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 1 points (Kimi K2.5 63/100, Qwen3.5 397B-A17B 62/100, Claude Opus 4.1 47/100), so choose by what matters most for your work: Kimi K2.5 for raw capability. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within a point (Kimi K2.5 71/100, Qwen3.5 397B-A17B 70/100, Claude Opus 4.1 67/100), so choose by what matters most for your work: Kimi K2.5 for raw capability. The score weighs capability 83%, context window 17%.

  • CapabilityKimi K2.5Capabilities Index (ECI): Kimi K2.5 148.8 · Qwen3.5 397B-A17B 148.0 · Claude Opus 4.1 144.8
  • Lowest priceKimi K2.5Kimi K2.5 $1.20 · Qwen3.5 397B-A17B $1.35 · Claude Opus 4.1 $30.00 per 1M tokens (3:1 blend)
  • Longest contextKimi K2.5 and Qwen3.5 397B-A17BKimi K2.5 262,144 · Qwen3.5 397B-A17B 262,144 · Claude Opus 4.1 200,000 tokens
  • Widest inputsSame inputsKimi K2.5: Text, Images, Video · Claude Opus 4.1: Text, Images, PDFs · Qwen3.5 397B-A17B: Text, Images, Video
  • Self-hostingKimi K2.5 and Qwen3.5 397B-A17BPublishes downloadable weights
How the score is built
MeasureWeightKimi K2.5Claude Opus 4.1Qwen3.5 397B-A17B
CapabilityCapabilities Index (ECI)59%777376
Price29%44042
Context window12%433943
Overall100%63/10047/10062/100

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

How the score is built
MeasureWeightKimi K2.5Claude Opus 4.1Qwen3.5 397B-A17B
CapabilityCapabilities Index (ECI)83%777376
Context window17%433943
Overall100%71/10067/10070/100

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

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

Kimi K2.5 vs Claude Opus 4.1 vs Qwen3.5 397B-A17B specifications side by side
SpecificationKimi K2.5Moonshot AIClaude Opus 4.1AnthropicQwen3.5 397B-A17BAlibaba (Qwen)
Capability
Capabilities Index (ECI)148.8 (best)144.8148.0
ECI rank#74 of 159 (best)#94 of 159#76 of 159
ECI confidence interval147.3–150.3143.0–146.5145.9–150.1
ECI evaluation dateJan 27, 2026Aug 5, 2025Feb 13, 2026
Documented capabilitiesEarlier Kimi frontier model for long-context agents, coding, and multimodal workFlagship Claude model for deep reasoning, coding, and long-horizon agentsLarge open Qwen multimodal MoE for visual agents and long technical tasks
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
GPQA DiamondGraduate-level science questions87.6% (best)77.3%16K86.4%none
FrontierMath Tiers 1–3Research-level mathematicsNot published12.6%32K31.2%none (best)
OTIS Mock AIME 2024–2025Competition mathematics92.2% (best)68.9%27K88.9%
SWE-bench VerifiedFixing real GitHub issues73.8% (best)73.4%Not published
SimpleQA VerifiedShort factual questions34.3%Not publishedNot published
Publisher-reported benchmarks
SWE-Bench VerifiedPublisher-reported result70.8resolvedReported resultNot published76.4resolvedReported result
SWE-Atlas Codebase QnAPublisher-reported result13.1scoreReported resultNot publishedNot published
SWE-Atlas RefactoringPublisher-reported result20.95scoreReported resultNot publishedNot published
SWE-Atlas Test WritingPublisher-reported result25.77scoreReported resultNot publishedNot published
Price per million tokens
Input$0.60 (best)$15.00$0.60 (best)
Output$3.00 (best)$75.00$3.60
Cached inputNot publishedNot publishedNot published
Blended (3:1)$1.20 (best)$30.00$1.35
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 36 providersMedian of 18 providersOfficial Alibaba API
Limits
Context window262,144 tokens (best)200,000 tokens262,144 tokens (best)
Max inputNot publishedNot publishedNot published
Max output262,144 tokens (best)32,000 tokens65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesNo
AudioNoNoNo
VideoYesNoYes
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNot publishedNot publishedYes
File attachmentsYesYesYes
Temperature controlNoYesYes
Reasoning controlalwaysalwaysbudget
Availability
WeightsOpenProprietaryOpen
API model IDNot publishedNot publishedqwen3.5-397b-a17b
API providers36 (best)1936 (best)
ReleasedJan 27, 2026Aug 5, 2025Feb 15, 2026
Knowledge cutoffJan 2025Mar 31, 2025Not published
Publisher documentationModel weightsNot publishedPublisher documentation · Model weights
Source metadata updatedJan 27, 2026Aug 5, 2025Feb 15, 2026
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026Nov 22, 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.

  • Kimi K2.5$12.00
  • Claude Opus 4.1$300.00
  • Qwen3.5 397B-A17B$13.20
04 — Questions

Which should you choose?

Which is better: Kimi K2.5, Claude Opus 4.1 or Qwen3.5 397B-A17B?

It is close. Our weighted score puts them within 1 points (Kimi K2.5 63/100, Qwen3.5 397B-A17B 62/100, Claude Opus 4.1 47/100), so choose by what matters most for your work: Kimi K2.5 for raw capability. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within a point (Kimi K2.5 71/100, Qwen3.5 397B-A17B 70/100, Claude Opus 4.1 67/100), so choose by what matters most for your work: Kimi K2.5 for raw capability. The score weighs capability 83%, context window 17%.

Which is cheaper, Kimi K2.5, Claude Opus 4.1 or Qwen3.5 397B-A17B?

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); Claude Opus 4.1 costs $15.00 input / $75.00 output per million tokens (median across 18 API providers). 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 $30.00 for Claude Opus 4.1 (25× as much).

Which scores higher on benchmarks?

Kimi K2.5 scores higher on the Capabilities Index (ECI): Kimi K2.5 148.8 (#74 of 159), Qwen3.5 397B-A17B 148.0 (#76 of 159) and Claude Opus 4.1 144.8 (#94 of 159). The confidence ranges of the top two overlap (147.3–150.3 vs 145.9–150.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — Kimi K2.5 87.6%, Qwen3.5 397B-A17B 86.4%, Claude Opus 4.1 77.3%; OTIS Mock AIME 2024–2025 — Kimi K2.5 92.2%, Qwen3.5 397B-A17B 88.9%, Claude Opus 4.1 68.9%.

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, Kimi K2.5 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?

Kimi K2.5 and Qwen3.5 397B-A17B have the largest context windows (262,144 and 262,144 tokens), against 200,000 for Claude Opus 4.1. Maximum output per response: Kimi K2.5 up to 262,144, Claude Opus 4.1 up to 32,000, Qwen3.5 397B-A17B up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Kimi K2.5 accepts text, images and video; Claude Opus 4.1 accepts text, images and PDFs; Qwen3.5 397B-A17B 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; Claude Opus 4.1 is proprietary.

Which is newer?

Qwen3.5 397B-A17B is the newest, released Feb 15, 2026. Kimi K2.5 came out Jan 27, 2026; Claude Opus 4.1 came out Aug 5, 2025. Knowledge cutoff: Kimi K2.5 Jan 2025, Claude Opus 4.1 Mar 31, 2025.

How do you decide the winner?

This rating uses capability (59%, independent benchmark results); price (29%, blended price per million tokens (3 input : 1 output), log scale); context window (12%, 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 22, 2026.This rating uses capability (83%, independent benchmark results); context window (17%, 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 22, 2026.