Skip to main content

AnthropicMoonshot AILLM matchup

Claude Fable 5.2vs.Kimi K3

Which one is better?

Claude Fable 5.2 performs better than Kimi K3, but costs 2.7 times as much.

Fable 5.2 ahead
IntelligenceOverall index, 100 points = average
130.9

Claude Fable 5.2

Rank 1

101.1

Kimi K3

Rank 26

SpeedTokens per second
n/a

Claude Fable 5.2

61

Kimi K3

Kimi K3 cheaper
Price$ per 1M tokens
$16

Claude Fable 5.2

$6

Kimi K3

Popularity0 to 100
n/a

Claude Fable 5.2

86

Kimi K3

Rank 4 of 449

Choose Claude Fable 5.2 for

KnowledgeCodingMathematicsGeneralReasoningAgentsFinanceLegal (not certain)

Choose Kimi K3 for

No clear advantage

Where is the difference?

Strengths at a glance

Fable 5.2Kimi K3Median of all ranked models

11013015090CodingFable 5.2ReasoningFable 5.2MathematicsFable 5.2KnowledgeFable 5.2AgentsFable 5.2GeneralFable 5.2FinanceFable 5.2LegalslightlyFable 5.2
CodingFable 5.2 ahead
Fable 5.2131.6Rank 1
Kimi K397.3Rank 42
Median of ranked models87.4

95 % range: Fable 5.2 122.0 to 141.1, Kimi K3 90.2 to 104.4.

AreaFable 5.2Kimi K3

The same values and verdicts as the bars below. In the close-up the net starts at 90 points, just below the weaker model's lowest value; the reference group average is 100. Not in the net because a model has no own value there or the data are too thin: Multimodal, Health.

Fable 5.2 is ahead in 7 of 10 areas, Kimi K3 in none.

Fable 5.2 ahead: 7Fable 5.2 slightly ahead: 1too little data: 2

Areas in the overall index
KnowledgeFable 5.2 +50145.5 to 95.4
CodingFable 5.2 +34131.6 to 97.3
MathematicsFable 5.2 +34135.2 to 101.7
GeneralFable 5.2 +30132.8 to 102.7
ReasoningFable 5.2 +28124.9 to 97.2
AgentsFable 5.2 +27124.2 to 97.4
Multimodalonly Kimi K3 has a score
Specialist fields
FinanceFable 5.2 +18123.5 to 105.3
Legalleaning Fable 5.2not certain · 3 and 4 tests
Healthonly Kimi K3 has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Show 3 more areas that do not count toward the overall index
Cybersecurityonly Kimi K3 has a score
Productivityonly Kimi K3 has a score
Educationonly Kimi K3 has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Claude Fable 5.2 vs. Kimi K3 at the same effort

Both models measured at the same reasoning efforts. This shows whether a lead comes from the model or only from more compute.

lowFable 5.2 ahead
42.3 points gap across 11 shared test series
Overall index (max vs. max)Fable 5.2 ahead
Fable 5.2 130.9 vs. Kimi K3 101.1

The gap compares only the Artificial Analysis test series in which both models are measured at that effort. Tied below 3 points, ahead only beyond two standard errors.

Which model for which task?

Everyday tasks, translated from the area values above. Each row names the values it rests on.

Writing and debugging codeFable 5.2Coding 131.6 to 97.3
Maths and data analysisFable 5.2Mathematics 135.2 to 101.7, Reasoning 124.9 to 97.2
Facts and researchFable 5.2Knowledge 145.5 to 95.4
Agents and workflowsFable 5.2Agents 124.2 to 97.4
Security analysisopenCybersecurity without a score for Fable 5.2
Many requests on a small budgetKimi K3$16 to $6 per 1M tokens
Finance, legal and medical textsFable 5.2Finance 123.5 to 105.3, Legal 120.9 to 109.4, Health without a score for Fable 5.2
Images, screenshots and PDFsopenMultimodal without a score for Fable 5.2

Claude Fable 5.2 vs. Kimi K3 in our own test

The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

Claude Fable 5.2

Not tested yet

Kimi K3

Kimi K3: Pelican on a bicycle
A community classic for free-form SVG drawing.

Oct 1, 2026 · 173 s · $0.08

Test details
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
moonshotai/kimi-k3
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
5,145 tokens
Cost of the attempt
$0.0775
Response time
173.4 s
API model reported in response
moonshotai/kimi-k3
Pinned endpoint
Moonshot AI | moonshotai/kimi-k3-20260715
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

Earlier attempts (1)

  • Sep 7, 2026API request failedReasoning setting: high
SVG short test

There is no shared test round for this selection. Results from different rounds are not mixed.

Claude Fable 5.2 and Kimi K3 in the overall index

Every model with a place in the overall index, both models of this matchup highlighted. You can add or hide other models.

Overall index (Gradually Meta-Score v5)

20 of 94 models

4 models in this view are measured at a lower reasoning effort than max in the overall index. Dashed column: lower reasoning effort than the top.

Claude Fable 5.2max130.9
Gemini 4 Carbonhigh127.0
Claude Opus 5.5max125.6
Claude Fable 5.1max124.1
Claude Sonnet 5.5max121.8
Gemini 4 Argonhigh121.4
GPT-6 Astramax120.2
Muse Wonder Fullmax118.1
GPT-6.1 Solmax118.0
Claude Opus 5max117.4
Muse Wondermax113.3
Claude Fable 5max112.8
Kimi K3.1 Promax112.6
Muse Ember 1.0max110.4
GPT-6 Solmax109.1
GPT-5.6 Solmax109.1
Gemini 3.7 Flashhigh107.9
Muse Spark 1.3max107.3
Gemini 3.8 Flashhigh106.8
Kimi K3max101.1

Popularity compared

How often the models are searched for, used and mentioned, on a scale from 0 to 100.

Claude Fable 5.2 has no popularity score yet.

Over time

The timeline appears once both models have two values.

All data side by side

The better value is bold. For the overall index only when the gap is clear.

MetricClaude Fable 5.2Kimi K3
Intelligence
Overall indexpoints, 100 = reference group average, higher is better130.9101.1
RankRank 1 of 94Rank 26 of 94
Price per 1M tokens
Inputwhat you send$8$3
Outputwhat the model writes$40$15
Speed
Tokens per secondn/a61
Popularity
Popularitysearch, usage and mentions, 0 to 100n/a86Rank 4 of 449
Technical
Context windowhow much text the model reads at once1 M tokens≈ 1,500 A4 pages1.05 M tokens≈ 1,570 A4 pages
Knowledge cutoffJune 2026n/a
ReleasedNov 9, 2026Jul 16, 2026
AvailabilityActiveActive
Open weightsnoyes
  • Claude Fable 5.2, Batch pricing: $4 input and $20 output per million tokens, separate from standard API pricing. Source
  • Claude Fable 5.2, Fast pricing: $16 input and $80 output per million tokens. Fast is a separate serving mode. Source

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Is there a better choice?

Successor of Kimi K3Kimi K3.1 Pro

Overall index 112.6, rank 13$2 input and $10 output per 1M tokens

Fable 5.2 vs. Kimi K3.1 Pro
Cheaper than Kimi K3Claude Sonnet 5.5

Overall index 121.8, rank 5$2 input and $10 output per 1M tokens

Fable 5.2 vs. Claude Sonnet 5.5

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

A: Claude Fable 5.2B: Kimi K3

Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalClaude Fable 5.2: 13.3%Kimi K3: 16.7%Vals AIAs of 11/09/2026
Vals Legal IndexOverall · higher is betterTest setup not documented as identicalClaude Fable 5.2: 69.2%Kimi K3: 71.7%Vals AIAs of 11/09/2026
Tax Agent BenchControversy & Precedence Analysis (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 58.2%Kimi K3: 71.7%Vals AIAs of 11/09/2026
Vals Legal IndexTax Agent · higher is betterTest setup not documented as identicalClaude Fable 5.2: 67.0%Kimi K3: 68.5%Vals AIAs of 11/09/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalClaude Fable 5.2: 36.5%Kimi K3: 42.3%Vals AIAs of 11/09/2026
Tax Agent BenchCurrent & Temporal Analysis (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 66.0%Kimi K3: 72.3%Vals AIAs of 11/09/2026
Tax Agent BenchFact-Pattern Analysis (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 64.5%Kimi K3: 57.9%Vals AIAs of 11/09/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalClaude Fable 5.2: 20.0%Kimi K3: 16.7%Vals AIAs of 11/09/2026
Tax Agent BenchForms & Filings (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 60.1%Kimi K3: 69.0%Vals AIAs of 11/09/2026
Tax Agent BenchNumbers & Calculations (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 86.4%Kimi K3: 83.7%Vals AIAs of 11/09/2026
Show 3 more benchmarks
Tax Agent BenchRule & Source Lookup · higher is betterTest setup not documented as identicalClaude Fable 5.2: 46.7%Kimi K3: 46.7%Vals AIAs of 11/09/2026
Tax Agent BenchRule & Source Lookup (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 68.0%Kimi K3: 61.2%Vals AIAs of 11/09/2026
Tax Agent BenchWeighted Pass · higher is betterTest setup not documented as identicalClaude Fable 5.2: 67.0%Kimi K3: 68.5%Vals AIAs of 11/09/2026

More comparisons

Compare Claude Fable 5.2 and Kimi K3 with the models people compare them with most often.

Compare another matchup