← 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
64.9
Output speed
78.9
tokens/sec
Blended price
$20.00
per 1M tokens
Time to first token
82.56s

Model metadata

Model IDcd55210d-358e-4df1-ba9c-9acb5f186cc9
Slugclaude-fable-5
Release date2026-06-09
ProviderAnthropic
Provider sluganthropic
Output speed78.9 tok/s
Time to first token82.56s
Time to first answer82.56s
Blended price ($/1M)$20.00
Input price ($/1M)$10.00
Output price ($/1M)$50.00

All evaluation scores (15)

aime
aime 25
artificial analysis coding index62.00
artificial analysis intelligence index64.90
artificial analysis math index
gpqa92.6%
hle53.3%
ifbench63.5%
lcr70.0%
livecodebench
math 500
mmlu pro
scicode60.2%
tau298.5%
terminalbench hard62.9%

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

Benchmark data from Artificial Analysis.