Claude 3 Opus
Claude 3 Opus is a closed AI model from Anthropic with an index score of 108 (GPT-4 = 100), rank 184 of 217.
10891–124Index score#184 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
4 Mar 2024ReleasedReplaced by Claude Opus 4
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 workno evidence yet
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 9 leaderboards
The Model Indexthird-party tests, our method#184of 217 · 108
LMArena · Mathsmaths questions in chat#192of 346 · 1313LMArena · Instruction followingfollowing detailed instructions#205of 362 · 1314LMArena · Creative writingcreative writing#209of 360 · 1288LMArena · Textoverall chat quality, judged by people#212of 362 · 1322LMArena · Long promptslong, complex requests#208of 340 · 1330LMArena · Codingcoding questions in chat#220of 357 · 1355Epoch Capabilities Indexoverall capability from many benchmarks#153of 231 · 125.6LMArena · Visionunderstanding images#123of 145 · 1062Best attop three among current models
Replaced by Claude Opus 4; it no longer leads any category among current models.
Where to use itprices checked 18 Nov 2026
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released4 Mar 2024
Announcementanthropic.com ↗
Release entryClaude 3 (Opus/Sonnet; Haiku 03-13)
Scored asClaude 3 Opus
Output speed–
Hugging Faceclosed weights