Advertise here
#47

Claude Fable 5

Anthropic Release: 2026-06-10 Tested on: 2026-08-14 02:11 anthropic/claude-fable-5::medium
~9.5T total (~878B active)MoEClosedEstimated

Summary

Claude Fable 5 scores 8.6 on AI BENCHY and ranks #47. It has 10.0 reliability, a 78.8% pass rate, $3.004 total cost, and 15.01s average response time.

Model facts

Researched on 2026-08-12

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

Best estimate from public evidence; the vendor did not disclose every value. Unverified architecture reconstruction. Anthropic does not disclose parameter counts.

Parameter source Availability source

Score

8.6

Consistency

9.6

Reliability

10.0

Total Cost (Current Price)

$3.004

Total Output Tokens

42,146

Total Input Tokens

89,640

Input Price

$10.000 / 1M

Output Price

$50.000 / 1M

Tests Correct

Wrong Tests: 5

Attempt pass rate: 78.8%

Flaky tests

1

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

Response Time (avg)

15.01s

Response Time (max): 80.80s

Response Time (total): 330.15s

No answer: 3 Invalid tool call: 1 Wrong answer: 1

Hamster playing table tennis

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

#47 Claude Fable 5

medium
Cost
$0.606
Time
156.7s
Tokens
12,264 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:11 Re-test 8.6 10.0 $3.004 Current run
2026-07-16 22:30 New test added 8.6 10.0 $3.478 Compare
2026-06-10 13:28 Initial run 8.7 10.0 $3.165 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-08-14 12:51 $10.000 / 1M $50.000 / 1M

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 5mediumvsMuse Spark 1.1mediumClaude Fable 5mediumvsQwen3.6 Max PreviewmediumClaude Fable 5mediumvsMuse Spark 1.2mediumClaude Fable 5mediumvsQwen3.8 MaxlowClaude Fable 5mediumvsMuse Spark 1.2highClaude Fable 5mediumvsGPT-5.4mediumClaude Fable 5mediumvsClaude Opus 4.7mediumClaude Fable 5mediumvsGrok 4.5mediumClaude Fable 5mediumvsGLM 5.3 FlashmaxClaude Fable 5mediumvsMuse Spark 1.2low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 6.5 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 7.2
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 7.7 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models