Claude Sonnet 5
Claude Sonnet 5 is a closed AI model from Anthropic with an index score of 164 (GPT-4 = 100), rank 38 of 217.
164148–180Index score#38 of 217 models
$2.0/ $10Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
30 Jun 2026ReleasedReplaced by Claude Sonnet 5.5
Where it sitson the frontier
Claude Opus 4.6 reached this score 5 months earlier.
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#38of 217 · 164
LMArena · Codingcoding questions in chat#34of 357 · 1520LMArena · Instruction followingfollowing detailed instructions#38of 362 · 1467LMArena · Long promptslong, complex requests#40of 340 · 1481LMArena · Mathsmaths questions in chat#44of 346 · 1472LMArena · Textoverall chat quality, judged by people#54of 362 · 1461Epoch Capabilities Indexoverall capability from many benchmarks#35of 231 · 156.9LMArena · Creative writingcreative writing#56of 360 · 1434LMArena · Visionunderstanding images#38of 145 · 1261LMArena · WebDevbuilding web apps and front ends#51of 133 · 1539LMArena · Documentsworking with long documents#19of 40 · 1460LMArena · Searchanswering with web search#24of 41 · 1188Best 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
Released30 Jun 2026
Announcementanthropic.com ↗
Release entryClaude Sonnet 5
Scored asClaude Sonnet 5
Output speed–
Hugging Faceclosed weights