Claude Opus 4
Claude Opus 4 is a closed AI model from Anthropic with an index score of 136 (GPT-4 = 100), rank 109 of 217.
136120–151Index score#109 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
22 May 2025ReleasedReplaced by Claude Opus 4.1
Where it sitson the frontier
Gemini 2.5 Pro reached this score 2 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsevidence
Long tasksevidence
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 10 leaderboards
The Model Indexthird-party tests, our method#109of 217 · 136
LMArena · Creative writingcreative writing#57of 360 · 1433LMArena · Long promptslong, complex requests#57of 340 · 1466LMArena · Instruction followingfollowing detailed instructions#65of 362 · 1444LMArena · Codingcoding questions in chat#73of 357 · 1499LMArena · Textoverall chat quality, judged by people#100of 362 · 1426LMArena · Mathsmaths questions in chat#107of 346 · 1421Epoch Capabilities Indexoverall capability from many benchmarks#106of 231 · 142.9LMArena · Visionunderstanding images#74of 145 · 1208LMArena · Searchanswering with web search#39of 41 · 1127Best attop three among current models
Where to use itprices checked 18 Nov 2026
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released22 May 2025
Announcementanthropic.com ↗
Release entryClaude Opus 4 + Sonnet 4
Scored asClaude Opus 4
Output speed–
Hugging Faceclosed weights