0

Claude Opus 4.5

Closed

Claude Opus 4.5 is an AI model from Anthropic.

Publisher
Anthropic
Family
Claude
Context
200K
Input
Output
License
proprietary
Released
24 Nov 2025

Cite

Notes

Only stored in your browser.

Attribution

Attribution policy →
Context
200K
Input
$6.25
/1M tok
Output
$25
/1M tok
Blended
$10.94
#399/ 414/1M · 3:1
Speed
55
#166/ 414tok/s
Cache read
$0.50
0.08x input
Cache write
$6.25
1.00x input

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

Reported on 38 evals across 13 domains - best 100.0% on Nsa Codebreaker · #1 of 4

Reported eval scores

38
Terminal Bench 2 Verified61.8
Skillsbench45.3
Nsa Codebreaker100
Browser Nav Challenge16.7
Hanabi12.1
Infraresolutionbench83.5
Curvebench Env35.6
Curvebench Hard Env6.1
SWE-bench Verified79.2
LiveCodeBench73.8
PubMedQA: A Dataset for Biomedical Research Question Answering77.5
MMLU-Pro88.9
LiveBench78.1
Humanity's Last Exam (HLE)12.9
SciCode47
GPQA Diamond81
GPQA (Full Set)84.7
LiveBench - Coding79.7
LiveBench - Language81.3
Terminal-Bench (Hard)40.9
LiveBench - Math90.4
LiveBench - Data Analysis74.4
SWE-bench Multilingual70.7
LiveBench - Reasoning80.1
IFBench43
LiveBench - Instruction Following62.5
τ²-bench (Tau²-bench)86.3
IDE-Bench83.8
Vibe Code Bench v1.120.6
MedScribe83.2
MedCode45.2
TaxEval v274.3
MortgageTax67.7
CorpFin v261.3
ProofBench36
AIME 2025: Problems from the American Invitational Mathematics Examination62.7
SAGE45
FrontierMath20.7