Claude 3.5 Sonnet (Jun 2024)
Claude 3.5 Sonnet (Jun 2024) is a closed AI model from Anthropic with an index score of 113 (GPT-4 = 100), rank 168 of 217.
11397–129Index score#168 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
20 Jun 2024ReleasedReplaced by Claude 3.5 Sonnet
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 workno evidence yet
Novel problemsno evidence yet
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#168of 217 · 113
LMArena · Creative writingcreative writing#125of 360 · 1371LMArena · Codingcoding questions in chat#143of 357 · 1436LMArena · Instruction followingfollowing detailed instructions#149of 362 · 1374LMArena · Long promptslong, complex requests#143of 340 · 1397LMArena · Textoverall chat quality, judged by people#158of 362 · 1374LMArena · Mathsmaths questions in chat#174of 346 · 1352Epoch Capabilities Indexoverall capability from many benchmarks#135of 231 · 133.3LMArena · Visionunderstanding images#93of 145 · 1161Best attop three among current models
Replaced by Claude 3.5 Sonnet; 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
Released20 Jun 2024
Announcementanthropic.com ↗
Release entryClaude 3.5 Sonnet
Scored asClaude 3.5 Sonnet
Output speed–
Hugging Faceclosed weights