Claude 3.5 Haiku
Claude 3.5 Haiku is a closed AI model from Anthropic with an index score of 109 (GPT-4 = 100), rank 179 of 217.
10993–125Index score#179 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
4 Nov 2024ReleasedReplaced by Claude Haiku 4.5
Where it sitson the frontier
GPT-4o reached this score 6 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 9 leaderboards
The Model Indexthird-party tests, our method#179of 217 · 109
LMArena · Creative writingcreative writing#187of 360 · 1305LMArena · Codingcoding questions in chat#189of 357 · 1386LMArena · Long promptslong, complex requests#184of 340 · 1346LMArena · Instruction followingfollowing detailed instructions#198of 362 · 1316LMArena · Textoverall chat quality, judged by people#208of 362 · 1325LMArena · Mathsmaths questions in chat#217of 346 · 1287Epoch Capabilities Indexoverall capability from many benchmarks#154of 231 · 124.8LMArena · Visionunderstanding images#109of 145 · 1127Best attop three among current models
Replaced by Claude Haiku 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
Released4 Nov 2024
Announcementanthropic.com ↗
Release entryClaude 3.5 Sonnet (new) + 3.5 Haiku (avail. 11-04)
Scored asClaude 3.5 Haiku
Output speed–
Hugging Faceclosed weights