← All benchmarks

Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

Anthropic · Released 2026-06-09 · Independent benchmark scores from Artificial Analysis

Intelligence Index
49.7
Output speed
69.3
tokens/sec
Blended price
$20.00
per 1M tokens
Time to first token
57.77s

Model metadata

Model IDcd55210d-358e-4df1-ba9c-9acb5f186cc9
Slugclaude-fable-5
Release date2026-06-09
ProviderAnthropic
Provider sluganthropic
Output speed69.3 tok/s
Time to first token57.77s
Time to first answer57.77s
Blended price ($/1M)$20.00
Input price ($/1M)$10.00
Output price ($/1M)$50.00

All evaluation scores (17)

aime
aime 25
artificial analysis coding index76.50
artificial analysis intelligence index49.70
artificial analysis math index
gpqa92.6%
hle55.5%
ifbench63.5%
lcr82.3%
livecodebench
math 500
mmlu pro
scicode61.0%
tau banking38.1%
tau298.5%
terminalbench hard62.9%
terminalbench v2 184.6%

Source: artificialanalysis.ai/models/claude-fable-5

Benchmark data from Artificial Analysis.