0

Claude Opus 4.8

Claude Opus 4.8 (Adaptive Reasoning, Max Effort) is an AI model from Anthropic.

Publisher
Anthropic
Family
Claude
Context
1M
Input
Output
Released
28 May 2026

Cite

Notes

Only stored in your browser.

Attribution

Attribution policy →
Context
1M
Input
$5
/1M tok
Output
$25
/1M tok
Blended
$10
#423/ 441/1M · 3:1
Speed
0
#110/ 441tok/s
Cache read
$0.25
0.05x input
Cache write
$3.13
0.63x input

Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter

Reported on 38 evals across 21 domains - best 94.4% on τ²-bench (Tau²-bench) · #16 of 321

Reported eval scores

38
LiveBench - Reasoning89.7
Terminal-Bench (Hard)58.3
LiveBench - Data Analysis78.3
LiveBench - Language81.4
LiveBench - Coding79.3
IFBench62.2
LiveBench - Math84.3
LiveBench - Instruction Following67.4
Humanity's Last Exam (HLE)48.7
LiveBench80.1
Vals Index70.4
SAGE54.8
GPQA Diamond92
SciCode53.5
MortgageTax69.9
TaxEval v275.6
CorpFin v266.7
Finance Agent (v2)53.9
τ²-bench (Tau²-bench)94.4
OSWorld-Verified83.4