ZMIME
Comparison · 2 models · Updated Nov 22, 2026

Claude Fable 5.1 vs Kimi K3

Too close to call on our weighted score (Claude Fable 5.1 65, Kimi K3 65). The right pick depends on what you value most.Claude Fable 5.1 comes out ahead, 87 to 82 on our weighted score, though Kimi K3 is 3.3× cheaper per token.

  1. Anthropic

    Claude Fable 5.1

    Released Sep 1, 2026

    65/100
    • ECI167.1
    • Price$10.00 / $50.00
    • Context1M
  2. Moonshot AI

    Kimi K3

    Released Jul 16, 2026Latest

    65/100
    • ECI158.6
    • Price$3.00 / $15.00
    • Context1.05M
  3. Our pick

    Anthropic

    Claude Fable 5.1

    Released Sep 1, 2026

    87/100
    • ECI167.1
    • Price$10.00 / $50.00
    • Context1M
  4. Moonshot AI

    Kimi K3

    Released Jul 16, 2026Latest

    82/100
    • ECI158.6
    • Price$3.00 / $15.00
    • Context1.05M
  5. Add a model

    Make it a three-way comparison.

01 — Verdict

Too close to callClaude Fable 5.1 is our pick

It is close. Our weighted score puts them within a point (Claude Fable 5.1 65/100, Kimi K3 65/100), so choose by what matters most for your work: Claude Fable 5.1 for raw capability, Kimi K3 on price and Kimi K3 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Claude Fable 5.1 is the better all-round choice, scoring 87/100 against Kimi K3 (82). It leads on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityClaude Fable 5.1Capabilities Index (ECI): Claude Fable 5.1 167.1 · Kimi K3 158.6
  • Lowest priceKimi K3Kimi K3 $6.00 · Claude Fable 5.1 $20.00 per 1M tokens (3:1 blend)
  • Longest contextKimi K3Kimi K3 1,048,576 · Claude Fable 5.1 1,000,000 tokens
  • Widest inputsSame inputsClaude Fable 5.1: Text, Images, PDFs · Kimi K3: Text, Images, Video
  • Self-hostingKimi K3Publishes downloadable weights
How the score is built
MeasureWeightClaude Fable 5.1Kimi K3
CapabilityCapabilities Index (ECI)50%9486
Price25%012
Inputs & features15%8080
Context window10%6465
Overall100%65/10065/100
How the score is built
MeasureWeightClaude Fable 5.1Kimi K3
CapabilityCapabilities Index (ECI)67%9486
Inputs & features20%8080
Context window13%6465
Overall100%87/10082/100
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.

Claude Fable 5.1 vs Kimi K3 specifications side by side
SpecificationClaude Fable 5.1AnthropicKimi K3Moonshot AI
Capability
Capabilities Index (ECI)167.1 (best)158.6
ECI rank#8 of 159 (best)#26 of 159
ECI confidence interval164.4–170.1156.7–160.8
ECI evaluation dateSep 1, 2026Jul 16, 2026
Documented capabilitiesClaude model for demanding reasoning and long-horizon agentic workMultimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Model parametersNot publishedNot published
Output modalitiesTextText
GPQA DiamondGraduate-level science questionsNot published93.1%max
FrontierMath Tiers 1–3Research-level mathematics90.2%max (best)72.2%max
OTIS Mock AIME 2024–2025Competition mathematics100%max (best)97.2%max
SimpleQA VerifiedShort factual questions70.8%max (best)50.6%max
Publisher-reported benchmarks
Terminal-Bench-Science 0.1production safeguards with fallback52.6scoreReported resultSep 1, 2026Not published
Terminal-Bench 4.0production safeguards with fallback55.8scoreReported resultSep 1, 2026Not published
GDPval-AA 2production safeguards with fallback1853EloReported resultSep 1, 2026Not published
OSWorld 2.0 · August 2026 task releaseproduction safeguards; interventions score zero; no fallback77.9partial scoreReported resultSep 1, 2026Not published
OSWorld 2.0 · August 2026 task releaseproduction safeguards; interventions score zero; no fallback41.7strict success rateReported resultSep 1, 2026Not published
Humanity's Last Examwithout tools; production safeguards with fallback60.9scoreReported resultSep 1, 2026Not published
Humanity's Last Examwith tools; production safeguards with fallback65scoreReported resultSep 1, 2026Not published
AutomationBenchproduction safeguards with fallback31.4pass rateReported resultSep 1, 2026Not published
CursorBench 3.2.0max effort; production safeguards with fallback73.4scoreReported resultSep 1, 2026Not published
DeepSWE 1.1max effortNot published67.5resolve rateReported resultJul 16, 2026
Terminal-Bench 2.1max effortNot published88.3accuracyReported resultJul 16, 2026
FrontierSWEmax effortNot published81.2dominance scoreReported resultJul 16, 2026
Program Benchmax effortNot published77.8scoreReported resultJul 16, 2026
SWE Marathon 1.1max effortNot published42resolve rateReported resultJul 16, 2026
GDPval-AA v2max effortNot published1668EloReported resultJul 16, 2026
AA-Briefcasemax effortNot published1548EloReported resultJul 16, 2026
AutomationBench · 600-task public subsetmax effortNot published30.8success rateReported resultJul 16, 2026
JobBenchmax effortNot published52.9scoreReported resultJul 16, 2026
SpreadsheetBench 2max effortNot published34.8scoreReported resultJul 16, 2026
BrowseCompmax effort, context compactionNot published91.2accuracyReported resultJul 16, 2026
CharXiv Reasoningmax effort, with toolsNot published91.3accuracyReported resultJul 16, 2026
ZeroBenchmax effort, with toolsNot published41pass@5Reported resultJul 16, 2026
Price per million tokens
Input$10.00$3.00 (best)
Output$50.00$15.00 (best)
Cached input$0.25 (best)$0.30
Blended (3:1)$20.00$6.00 (best)
Long-context rateSame rateSame rate
Price sourceOfficial Anthropic APIOfficial Moonshot AI API
Limits
Context window1,000,000 tokens1,048,576 tokens (best)
Max inputNot publishedNot published
Max output128,000 tokens1,048,576 tokens (best)
Inputs and features
TextYesYes
ImagesYesYes
PDFsYesNo
AudioNoNo
VideoNoYes
ReasoningYeslow · medium · high · xhigh · maxYeslow · high · max
Tool callingYesYes
Structured outputYesYes
File attachmentsYesYes
Temperature controlNoNo
Reasoning controlefforteffort
Availability
WeightsProprietaryOpen
API model IDclaude-fable-5-1kimi-k3
API providers5193 (best)
ReleasedSep 1, 2026Jul 16, 2026
Knowledge cutoffJun 2026Not published
Publisher documentationPublisher documentationPublisher documentation · Model weights
Source metadata updatedSep 1, 2026Jul 16, 2026
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 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.

  • Claude Fable 5.1$200.00
  • Kimi K3$60.00
04 — Questions

Which should you choose?

Which is better: Claude Fable 5.1 or Kimi K3?

It is close. Our weighted score puts them within a point (Claude Fable 5.1 65/100, Kimi K3 65/100), so choose by what matters most for your work: Claude Fable 5.1 for raw capability, Kimi K3 on price and Kimi K3 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Claude Fable 5.1 is the better all-round choice, scoring 87/100 against Kimi K3 (82). It leads on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, Claude Fable 5.1 or Kimi K3?

Kimi K3 is cheaper at $3.00 input / $15.00 output per million tokens (official Moonshot AI API price). Claude Fable 5.1 costs $10.00 input / $50.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $6.00 per million tokens for Kimi K3 versus $20.00 for Claude Fable 5.1 (3.3× as much).

Which scores higher on benchmarks?

Claude Fable 5.1 scores higher on the Capabilities Index (ECI): Claude Fable 5.1 167.1 (#8 of 159) and Kimi K3 158.6 (#26 of 159). Their confidence ranges do not overlap (164.4–170.1 vs 156.7–160.8), so the gap is a real one. On individual benchmarks: FrontierMath Tiers 1–3 — Claude Fable 5.1 90.2%, Kimi K3 72.2%; OTIS Mock AIME 2024–2025 — Claude Fable 5.1 100%, Kimi K3 97.2%; SimpleQA Verified — Claude Fable 5.1 70.8%, Kimi K3 50.6%.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Fable 5.1 and Kimi K3 yet, so there is no like-for-like coding score. On overall capability, Claude Fable 5.1 leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Which has the bigger context window?

Kimi K3 has the largest context window at 1,048,576 tokens, against 1,000,000 for Claude Fable 5.1. Maximum output per response: Claude Fable 5.1 up to 128,000, Kimi K3 up to 1,048,576 tokens.

Which can read images, PDFs, audio or video?

Claude Fable 5.1 accepts text, images and PDFs; Kimi K3 accepts text, images and video. They handle the same number of input types.

Are any of these open source?

Kimi K3 publishes its weights and can be self-hosted; Claude Fable 5.1 is proprietary.

Which is newer?

Claude Fable 5.1 is the newest, released Sep 1, 2026. Kimi K3 came out Jul 16, 2026. Knowledge cutoff: Claude Fable 5.1 Jun 2026.

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 22, 2026.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 22, 2026.