Claude Sonnet 4.5
Claude Sonnet 4.5 is a closed AI model from Anthropic with an index score of 144 (GPT-4 = 100), rank 83 of 217.
144129–160Index score#83 of 217 models
$3.0/ $15Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
29 Sep 2025ReleasedReplaced by Claude Sonnet 4.6
Where it sitson the frontier
o3 reached this score 5 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 11 leaderboards
The Model Indexthird-party tests, our method#83of 217 · 144
LMArena · Creative writingcreative writing#28of 360 · 1455LMArena · Long promptslong, complex requests#33of 340 · 1485LMArena · Codingcoding questions in chat#35of 357 · 1519LMArena · Instruction followingfollowing detailed instructions#42of 362 · 1463LMArena · Textoverall chat quality, judged by people#60of 362 · 1456LMArena · Mathsmaths questions in chat#63of 346 · 1455Epoch Capabilities Indexoverall capability from many benchmarks#79of 231 · 147.6LMArena · Documentsworking with long documents#24of 40 · 1449LMArena · WebDevbuilding web apps and front ends#93of 133 · 1394LMArena · Searchanswering with web search#31of 41 · 1159Best 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
Released29 Sep 2025
Announcementanthropic.com ↗
Release entryClaude Sonnet 4.5
Scored asClaude Sonnet 4.5
Output speed–
Hugging Faceclosed weights