Claude Sonnet 4.6
Claude Sonnet 4.6 is a closed AI model from Anthropic with an index score of 159 (GPT-4 = 100), rank 56 of 217.
159143–175Index score#56 of 217 models
$3.0/ $15Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
17 Feb 2026ReleasedReplaced by Claude Sonnet 5
Where it sitson the frontier
Gemini 3 Pro reached this score 3 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsevidence
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#56of 217 · 159
LMArena · Long promptslong, complex requests#21of 340 · 1492LMArena · Codingcoding questions in chat#23of 357 · 1528LMArena · Instruction followingfollowing detailed instructions#27of 362 · 1475LMArena · Creative writingcreative writing#35of 360 · 1449LMArena · Textoverall chat quality, judged by people#42of 362 · 1472LMArena · Mathsmaths questions in chat#59of 346 · 1461LMArena · Visionunderstanding images#27of 145 · 1275LMArena · Documentsworking with long documents#8of 40 · 1482Epoch Capabilities Indexoverall capability from many benchmarks#56of 231 · 152.9LMArena · Searchanswering with web search#12of 41 · 1221LMArena · WebDevbuilding web apps and front ends#55of 133 · 1522Best 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
Released17 Feb 2026
Announcementanthropic.com ↗
Release entryClaude Sonnet 4.6
Scored asClaude Sonnet 4.6
Output speed–
Hugging Faceclosed weights