AI BENCHY
Advertise here
#130

Claude Fable 5.1

Anthropic Release: 2026-09-02 Tested on: 2026-09-02 02:04 anthropic/claude-fable-5.1::low
~9.5T total (~878B active)MoEClosedEstimated
(high) (medium) (low)

Summary

Claude Fable 5.1 scores 6.9 on AI BENCHY and ranks #130. It has 10.0 reliability, a 56.1% pass rate, $2.565 total cost, and 10.33s average response time.

What makes Claude Fable 5.1 unique: It stands out most in Combined, where it ranks #1, while Anti-AI Tricks is its weakest area at #17.

Model facts

Researched on 2026-09-02

Estimated
Parameters
~9.5T total (~878B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Anthropic does not disclose parameter counts or architecture; estimates follow the Claude Fable 5 family record.

Parameter source Availability source

Score

6.9

Consistency

9.2

Reliability

10.0

Total Cost (Current Price)

$2.565

Total Output Tokens

24,375

Total Input Tokens

134,582

Input Price

$10.000 / 1M

Output Price

$50.000 / 1M

Tests Correct

Wrong Tests: 11

Attempt pass rate: 56.1%

Flaky tests

2

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

10.33s

Response Time (max): 33.10s

Response Time (total): 227.37s

Extra formatting: 4 Wrong answer: 4 Did not follow instructions: 3

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#130 Claude Fable 5.1

low
Cost
$0.126
Time
28.5s
Tokens
2,652 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Claude Fable 5.1lowvsKAT-Coder-Pro V2.5mediumClaude Fable 5.1lowvsQwen3.7 FlashmediumClaude Fable 5.1lowvsKimi K2.5mediumClaude Fable 5.1lowvsSeed-2.0-CodehighClaude Fable 5.1lowvsSeed-2.0-MinimediumClaude Fable 5.1lowvsGemini 3.5 FlashnoneClaude Fable 5.1lowvsGrok 4.20mediumClaude Fable 5.1lowvsQwen3.6 FlashmediumClaude Fable 5.1lowvsMercury 2mediumClaude Fable 5.1lowvsStep 3.7 Flashhigh

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 6.5 10.0
Coding 3.4 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 4.1 4.4
General Intelligence 10.0 10.0
Instructions following 6.5 10.0
Puzzle Solving 7.7 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models