Claude Sonnet 4
Claude Sonnet 4 is a closed AI model from Anthropic with an index score of 133 (GPT-4 = 100), rank 120 of 217.
133117–149Index score#120 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
22 May 2025ReleasedReplaced by Claude Sonnet 4.5
Where it sitson the frontier
o1 reached this score 6 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 9 leaderboards
The Model Indexthird-party tests, our method#120of 217 · 133
LMArena · Long promptslong, complex requests#89of 340 · 1443LMArena · Creative writingcreative writing#96of 360 · 1396LMArena · Instruction followingfollowing detailed instructions#101of 362 · 1416LMArena · Codingcoding questions in chat#103of 357 · 1474LMArena · Textoverall chat quality, judged by people#131of 362 · 1402LMArena · Mathsmaths questions in chat#130of 346 · 1404Epoch Capabilities Indexoverall capability from many benchmarks#110of 231 · 141.9LMArena · Visionunderstanding images#76of 145 · 1206Best attop three among current models
Replaced by Claude Sonnet 4.5; 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
Released22 May 2025
Announcementanthropic.com ↗
Release entryClaude Opus 4 + Sonnet 4
Scored asClaude Sonnet 4
Output speed–
Hugging Faceclosed weights