Claude Opus 4.7
Claude Opus 4.7 is a closed AI model from Anthropic with an index score of 167 (GPT-4 = 100), rank 33 of 217.
167151–183Index score#33 of 217 models
$5.0/ $25Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
16 Apr 2026ReleasedReplaced by Claude Opus 4.8
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 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#33of 217 · 167
LMArena · Codingcoding questions in chat#4of 357 · 1551LMArena · Visionunderstanding images#2of 145 · 1300LMArena · Long promptslong, complex requests#6of 340 · 1515LMArena · Instruction followingfollowing detailed instructions#7of 362 · 1503LMArena · Textoverall chat quality, judged by people#8of 362 · 1501LMArena · Creative writingcreative writing#9of 360 · 1489LMArena · Mathsmaths questions in chat#11of 346 · 1503LMArena · Documentsworking with long documents#5of 40 · 1496Epoch Capabilities Indexoverall capability from many benchmarks#31of 231 · 157.5LMArena · Searchanswering with web search#9of 41 · 1230LMArena · WebDevbuilding web apps and front ends#46of 133 · 1557Best 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
Released16 Apr 2026
Announcementanthropic.com ↗
Release entryClaude Opus 4.7
Scored asClaude Opus 4.7
Output speed–
Hugging Faceclosed weights