ZMIME
Comparison · 3 models · Updated Nov 22, 2026

Claude Fable 5.1 vs GPT-6 Astra vs Kimi K3

Too close to call on our weighted score (GPT-6 Astra 66, Claude Fable 5.1 65, Kimi K3 65). The right pick depends on what you value most.Too close to call on our weighted score (GPT-6 Astra 89, Claude Fable 5.1 87, Kimi K3 82). The right pick depends on what you value most.

  1. Anthropic

    Claude Fable 5.1

    Released Sep 1, 2026

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

    GPT-6 Astra

    Released Sep 4, 2026

    66/100
    • ECI169.2
    • Price$10.00 / $50.00
    • Context1.05M
  3. Moonshot AI

    Kimi K3

    Released Jul 16, 2026Latest

    65/100
    • ECI158.6
    • Price$3.00 / $15.00
    • Context1.05M
  4. Anthropic

    Claude Fable 5.1

    Released Sep 1, 2026

    87/100
    • ECI167.1
    • Price$10.00 / $50.00
    • Context1M
  5. OpenAI

    GPT-6 Astra

    Released Sep 4, 2026

    89/100
    • ECI169.2
    • Price$10.00 / $50.00
    • Context1.05M
  6. Moonshot AI

    Kimi K3

    Released Jul 16, 2026Latest

    82/100
    • ECI158.6
    • Price$3.00 / $15.00
    • Context1.05M
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 1 points (GPT-6 Astra 66/100, Claude Fable 5.1 65/100, Kimi K3 65/100), so choose by what matters most for your work: GPT-6 Astra for raw capability and Kimi K3 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.It is close. Our weighted score puts them within 1 points (GPT-6 Astra 89/100, Claude Fable 5.1 87/100, Kimi K3 82/100), so choose by what matters most for your work: GPT-6 Astra for raw capability and Kimi K3 on price. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityGPT-6 AstraCapabilities Index (ECI): GPT-6 Astra 169.2 · Claude Fable 5.1 167.1 · Kimi K3 158.6
  • Lowest priceKimi K3Kimi K3 $6.00 · Claude Fable 5.1 $20.00 · GPT-6 Astra $20.00 per 1M tokens (3:1 blend)
  • Longest contextGPT-6 Astra and Kimi K3GPT-6 Astra 1,050,000 · Kimi K3 1,048,576 · Claude Fable 5.1 1,000,000 tokens
  • Widest inputsSame inputsClaude Fable 5.1: Text, Images, PDFs · GPT-6 Astra: Text, Images, PDFs · Kimi K3: Text, Images, Video
  • Self-hostingKimi K3Publishes downloadable weights
How the score is built
MeasureWeightClaude Fable 5.1GPT-6 AstraKimi K3
CapabilityCapabilities Index (ECI)50%949686
Price25%0012
Inputs & features15%808080
Context window10%646565
Overall100%65/10066/10065/100
How the score is built
MeasureWeightClaude Fable 5.1GPT-6 AstraKimi K3
CapabilityCapabilities Index (ECI)67%949686
Inputs & features20%808080
Context window13%646565
Overall100%87/10089/10082/100
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 GPT-6 Astra vs Kimi K3 specifications side by side
SpecificationClaude Fable 5.1AnthropicGPT-6 AstraOpenAIKimi K3Moonshot AI
Capability
Capabilities Index (ECI)167.1169.2 (best)158.6
ECI rank#8 of 159#4 of 159 (best)#26 of 159
ECI confidence interval164.4–170.1166.4–172.5156.7–160.8
ECI evaluation dateSep 1, 2026Sep 3, 2026Jul 16, 2026
Documented capabilitiesClaude model for demanding reasoning and long-horizon agentic workGPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
GPQA DiamondGraduate-level science questionsNot published95.8%max (best)93.1%max
FrontierMath Tiers 1–3Research-level mathematics90.2%max93.7%max (best)72.2%max
OTIS Mock AIME 2024–2025Competition mathematics100%max (best)100%max (best)97.2%max
SimpleQA VerifiedShort factual questions70.8%max75.6%max (best)50.6%max
Publisher-reported benchmarks
Terminal-Bench-Science 0.1production safeguards with fallback52.6scoreReported resultSep 1, 2026Not publishedNot published
Terminal-Bench 4.0production safeguards with fallback55.8scoreReported resultSep 1, 2026Not publishedNot published
GDPval-AA 2production safeguards with fallback1853EloReported resultSep 1, 2026Not publishedNot published
OSWorld 2.0 · August 2026 task releaseproduction safeguards; interventions score zero; no fallback77.9partial scoreReported resultSep 1, 2026Not publishedNot published
OSWorld 2.0 · August 2026 task releaseproduction safeguards; interventions score zero; no fallback41.7strict success rateReported resultSep 1, 2026Not publishedNot published
Humanity's Last Examwithout tools; production safeguards with fallback60.9scoreReported resultSep 1, 2026Not publishedNot published
Humanity's Last Examwith tools; production safeguards with fallback65scoreReported resultSep 1, 2026Not publishedNot published
AutomationBenchproduction safeguards with fallback31.4pass rateReported resultSep 1, 2026Not publishedNot published
CursorBench 3.2.0max effort; production safeguards with fallback73.4scoreReported resultSep 1, 2026Not publishedNot published
Agents' Last ExamPublisher-reported resultNot published59.3Reported resultSep 3, 2026Not published
OSWorld 2.0 · V2-Offline (v2026.08.08)Publisher-reported resultNot published72.6partial scoreReported resultSep 3, 2026Not published
ScreenSpot-Prono toolsNot published92.7accuracyReported resultSep 3, 2026Not published
AutomationBenchPublisher-reported resultNot published41.4success rateReported resultSep 3, 2026Not published
BenchCADwith toolsNot published95.9geometric overlapReported resultSep 3, 2026Not published
BrowseCompPublisher-reported resultNot published91.5accuracyReported resultSep 3, 2026Not published
Terminal-Bench 4.0Publisher-reported resultNot published57.9success rateReported resultSep 3, 2026Not published
DeepSWE 1.1Publisher-reported resultNot published74.1resolve rateReported resultSep 3, 2026Not published
FrontierCode 1.1 · ExtendedPublisher-reported resultNot published64.5scoreReported resultSep 3, 2026Not published
Terminal-Bench Science 0.1Publisher-reported resultNot published64.6success rateReported resultSep 3, 2026Not published
FrontierMath v2 · Tier 4Publisher-reported resultNot published97.6accuracyReported resultSep 3, 2026Not published
GPQA DiamondPublisher-reported resultNot published96accuracyReported resultSep 3, 2026Not published
Humanity's Last Examwith toolsNot published57.2accuracyReported resultSep 3, 2026Not published
ExploitBenchwithout production safeguardsNot published100success rateReported resultSep 3, 2026Not published
SRE-Benchsingle attemptNot published88success rateReported resultSep 3, 2026Not published
ARC-AGI-3Publisher-reported resultNot published99.9RHAEReported resultSep 3, 2026Not published
Artificial Analysis Intelligence Index 4.1.1maxNot published61index scoreReported resultSep 3, 2026Not published
Artificial Analysis Coding Agent Index 1.4maxNot published67index scoreReported resultSep 3, 2026Not published
DeepSWE 1.1max effortNot publishedNot published67.5resolve rateReported resultJul 16, 2026
Terminal-Bench 2.1max effortNot publishedNot published88.3accuracyReported resultJul 16, 2026
FrontierSWEmax effortNot publishedNot published81.2dominance scoreReported resultJul 16, 2026
Program Benchmax effortNot publishedNot published77.8scoreReported resultJul 16, 2026
SWE Marathon 1.1max effortNot publishedNot published42resolve rateReported resultJul 16, 2026
GDPval-AA v2max effortNot publishedNot published1668EloReported resultJul 16, 2026
AA-Briefcasemax effortNot publishedNot published1548EloReported resultJul 16, 2026
AutomationBench · 600-task public subsetmax effortNot publishedNot published30.8success rateReported resultJul 16, 2026
JobBenchmax effortNot publishedNot published52.9scoreReported resultJul 16, 2026
SpreadsheetBench 2max effortNot publishedNot published34.8scoreReported resultJul 16, 2026
BrowseCompmax effort, context compactionNot publishedNot published91.2accuracyReported resultJul 16, 2026
CharXiv Reasoningmax effort, with toolsNot publishedNot published91.3accuracyReported resultJul 16, 2026
ZeroBenchmax effort, with toolsNot publishedNot published41pass@5Reported resultJul 16, 2026
Price per million tokens
Input$10.00$10.00$3.00 (best)
Output$50.00$50.00$15.00 (best)
Cached input$0.25 (best)$1.00$0.30
Blended (3:1)$20.00$20.00$6.00 (best)
Long-context rateSame rateOver 272K: $20.00 / $75.00Same rate
Price sourceOfficial Anthropic APIOfficial OpenAI APIOfficial Moonshot AI API
Limits
Context window1,000,000 tokens1,050,000 tokens (best)1,048,576 tokens
Max inputNot published922,000 tokensNot published
Max output128,000 tokens128,000 tokens1,048,576 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesYesNo
AudioNoNoNo
VideoNoNoYes
ReasoningYeslow · medium · high · xhigh · maxYeslow · medium · high · xhigh · maxYeslow · high · max
Tool callingYesYesYes
Structured outputYesYesYes
File attachmentsYesYesYes
Temperature controlNoNoNo
Reasoning controleffortefforteffort
Availability
WeightsProprietaryProprietaryOpen
API model IDclaude-fable-5-1gpt-6-astrakimi-k3
API providers515693 (best)
ReleasedSep 1, 2026Sep 4, 2026Jul 16, 2026
Knowledge cutoffJun 2026Apr 30, 2026Not published
Publisher documentationPublisher documentationPublisher documentationPublisher documentation · Model weights
Source metadata updatedSep 1, 2026Sep 4, 2026Jul 16, 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.

  • Claude Fable 5.1$200.00
  • GPT-6 Astra$200.00
  • Kimi K3$60.00
04 — Questions

Which should you choose?

Which is better: Claude Fable 5.1, GPT-6 Astra or Kimi K3?

It is close. Our weighted score puts them within 1 points (GPT-6 Astra 66/100, Claude Fable 5.1 65/100, Kimi K3 65/100), so choose by what matters most for your work: GPT-6 Astra for raw capability and Kimi K3 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.It is close. Our weighted score puts them within 1 points (GPT-6 Astra 89/100, Claude Fable 5.1 87/100, Kimi K3 82/100), so choose by what matters most for your work: GPT-6 Astra for raw capability and Kimi K3 on price. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, Claude Fable 5.1, GPT-6 Astra 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); GPT-6 Astra costs $10.00 input / $50.00 output per million tokens (official OpenAI 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) and $20.00 for GPT-6 Astra (3.3× as much).

Which scores higher on benchmarks?

GPT-6 Astra scores higher on the Capabilities Index (ECI): GPT-6 Astra 169.2 (#4 of 159), Claude Fable 5.1 167.1 (#8 of 159) and Kimi K3 158.6 (#26 of 159). The confidence ranges of the top two overlap (166.4–172.5 vs 164.4–170.1), so treat the gap as small. On individual benchmarks: FrontierMath Tiers 1–3 — GPT-6 Astra 93.7%, Claude Fable 5.1 90.2%, Kimi K3 72.2%; OTIS Mock AIME 2024–2025 — Claude Fable 5.1 100%, GPT-6 Astra 100%, Kimi K3 97.2%; SimpleQA Verified — GPT-6 Astra 75.6%, 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, GPT-6 Astra and Kimi K3 yet, so there is no like-for-like coding score. On overall capability, GPT-6 Astra 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-6 Astra and Kimi K3 have the largest context windows (1,050,000 and 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, GPT-6 Astra 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; GPT-6 Astra 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 and GPT-6 Astra is proprietary.

Which is newer?

GPT-6 Astra is the newest, released Sep 4, 2026. Claude Fable 5.1 came out Sep 1, 2026; Kimi K3 came out Jul 16, 2026. Knowledge cutoff: Claude Fable 5.1 Jun 2026, GPT-6 Astra Apr 30, 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.