Claude Opus 4.5
Claude Opus 4.5 is a closed AI model from Anthropic with an index score of 152 (GPT-4 = 100), rank 65 of 217.
152136–168Index score#65 of 217 models
$5.0/ $25Price per million tokensinput / output · via OpenRouter
200KContext windowtokens it reads at once
24 Nov 2025ReleasedReplaced by Claude Opus 4.6
Where it sitson the frontier
Among the first models to reach this score.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsno evidence yet
Long tasksevidence
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 11 leaderboards
The Model Indexthird-party tests, our method#65of 217 · 152
LMArena · Instruction followingfollowing detailed instructions#18of 362 · 1483LMArena · Creative writingcreative writing#20of 360 · 1469LMArena · Codingcoding questions in chat#20of 357 · 1530LMArena · Long promptslong, complex requests#20of 340 · 1494LMArena · Textoverall chat quality, judged by people#38of 362 · 1474LMArena · Mathsmaths questions in chat#43of 346 · 1472Epoch Capabilities Indexoverall capability from many benchmarks#60of 231 · 151.9LMArena · Documentsworking with long documents#16of 40 · 1466LMArena · WebDevbuilding web apps and front ends#65of 133 · 1493LMArena · Searchanswering with web search#25of 41 · 1179Best attop three among current models
Where to use itprices checked 18 Nov 2026
API providers 5 · per 1M tokens, in / out
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released24 Nov 2025
Announcementanthropic.com ↗
Release entryClaude Opus 4.5
Scored asClaude Opus 4.5
Output speed–
Hugging Faceclosed weights