Claude Haiku 5.5
Claude Haiku 5.5 is a closed AI model from Anthropic with an index score of 174 (GPT-4 = 100), rank 19 of 207.
174158–191Index score#19 of 207 models
$0.10/ $0.50Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
7 Oct 2026Released20 days ago
Where it sitson the frontier
GPT-5.5 reached this score 5 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 11 leaderboards
The Model Indexthird-party tests, our method#19of 207 · 174
Epoch Capabilities Indexoverall capability from many benchmarks#16of 243 · 159.3Artificial Analysis Intelligence Indexoverall capability across ten evaluations#20of 216 · 43LMArena · Instruction followingfollowing detailed instructions#82of 359 · 1429LMArena · WebDevbuilding web apps and front ends#31of 126 · 1586LMArena · Codingcoding questions in chat#88of 354 · 1485LMArena · Mathsmaths questions in chat#95of 346 · 1429LMArena · Textoverall chat quality, judged by people#104of 359 · 1425LMArena · Long promptslong, complex requests#113of 337 · 1422LMArena · Creative writingcreative writing#132of 357 · 1361LiveBench · Overalloverall, on regularly refreshed questions#12of 31 · 69.8Best attop three among current models
Not in the top three among current models on any category we track.
Where to use itprices checked 27 Oct 2026
API providers 5 · per 1M tokens, in / out
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released7 Oct 2026
Announcementanthropic.com ↗
Release entryClaude Haiku 5.5
Scored asClaude Haiku 5.5
Output speed234 tokens/s
Hugging Faceclosed weights
