readable AI benchmarks

Anthropic

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

reasoning · closed weights · Jun 9, 2026

Quality Score79.9
Value Score45.0
Reliability71.7
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
text, image
Output modalities
text
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$10.00
Output
$50.00
Cached Input
$1.00
Cached Output
$12.50
Cost per task
$3.14

Capability

Intelligence
62.1
Coding
76.5
Agentic
56.6
Omniscience
43.3
Correct
65.3%
Blended price
$7.70

Answer outcomes

Correct 65.3%Incorrect 22.0%Abstained 12.6%

Artificial Analysis benchmarks

GDPval-AA v2
62%
τ³-Banking
38%
Terminal-Bench v2.1
85%
SciCode
60%
Humanity’s Last Exam
55%
GPQA Diamond
93%
CritPt
29%
AA-Omniscience
72%
AA-LCR
77%

Similar models