Claude Opus 5
Claude Opus 5 is a closed AI model from Anthropic with an index score of 185 (GPT-4 = 100), rank 14 of 217.
185169–201Index score#14 of 217 models
$5.0/ $25Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
24 Jul 2026ReleasedReplaced by Claude Opus 5.5
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 problemsevidence
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 12 leaderboards
The Model Indexthird-party tests, our method#14of 217 · 185
LMArena · Mathsmaths questions in chat#3of 346 · 1521LMArena · Instruction followingfollowing detailed instructions#10of 362 · 1496LMArena · Long promptslong, complex requests#12of 340 · 1502LMArena · Textoverall chat quality, judged by people#14of 362 · 1490LMArena · Creative writingcreative writing#14of 360 · 1473Epoch Capabilities Indexoverall capability from many benchmarks#11of 231 · 164.7LMArena · Documentsworking with long documents#2of 40 · 1509LMArena · Codingcoding questions in chat#18of 357 · 1532LMArena · WebDevbuilding web apps and front ends#11of 133 · 1691LMArena · Visionunderstanding images#16of 145 · 1285LMArena · Searchanswering with web search#5of 41 · 1239Best 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 Jul 2026
Announcementanthropic.com ↗
Release entryClaude Opus 5
Scored asClaude Opus 5
Output speed–
Hugging Faceclosed weights