Advertise here
#13

Claude Fable 5.2

Anthropic Release: 2026-11-09 Tested on: 2026-11-10 00:55 anthropic/claude-fable-5.2::xhigh
~9.5T total (~878B active)MoEClosedEstimated
(xhigh) (high) (medium) (low)

Summary

Claude Fable 5.2 scores 9.6 on AI BENCHY and ranks #13. It has 9.2 reliability, a 94.2% pass rate, $10.319 total cost, and 33.44s average response time.

What makes Claude Fable 5.2 unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

Model facts

Researched on 2026-11-09

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

Best estimate from public evidence; the vendor did not disclose every value. API-only exact checkpoint (claude-fable-5-2). Anthropic does not disclose parameter counts or architecture; the low-confidence estimates follow the Claude Fable 5.1 family record.

Parameter source Availability source

Score

9.6

Consistency

9.6

Reliability

9.2

Total Cost (Current Price)

$10.319

Total Output Tokens

188,726

Total Input Tokens

346,216

Input Price

$8.000 / 1M

Output Price

$40.000 / 1M

Cache Read Price

$0.200 / 1M

Cache Write Price

$10.000 / 1M

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 2

Attempt pass rate: 94.2%

Flaky tests

1

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

Response Time (avg)

33.44s

Response Time (max): 440.05s

Response Time (total): 769.21s

Wrong answer: 2

Hamster playing table tennis

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

#13 Claude Fable 5.2

xhigh
Reached the allocated time limit (600 seconds) without receiving showcase output.
Cost
$0.000
Time
600.0s
Tokens
0 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 5.2xhighvsGPT-6.1 SolhighClaude Fable 5.2xhighvsGPT-5.6 SollowClaude Fable 5.2xhighvsGPT-6.1 SolmediumClaude Fable 5.2xhighvsGPT-6 AstralowClaude Fable 5.2xhighvsGemini 3.6 FlashmediumClaude Fable 5.2xhighvsGemini 3 Flash PreviewmediumClaude Fable 5.2xhighvsGemini 3.7 FlashhighClaude Fable 5.2xhighvsGPT-6.1 SollowClaude Fable 5.2xhighvsGPT-6 AstrahighClaude Fable 5.2xhighvsGPT-6.1 Terramedium

Category Breakdown

Category Score Consistency Tests Correct
Agentic 10.0 10.0
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 7.7 10.0
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 4.7 1.6

Compared models