haiku
tool judged 3% likely a named technique or architecture
See how it has spread across media tiers
Mentions over time
Table view
| Week | Articles | Sources |
|---|---|---|
| 2025-W16 | 1 | 1 |
| 2026-W02 | 1 | 1 |
| 2026-W09 | 1 | 1 |
| 2026-W11 | 8 | 1 |
| 2026-W12 | 1 | 1 |
| 2026-W24 | 1 | 1 |
| 2026-W29 | 2 | 2 |
| 2026-W30 | 1 | 1 |
| 2026-W33 | 1 | 1 |
| 2026-W36 | 1 | 1 |
| 2026-W37 | 1 | 1 |
| 2026-W40 | 7 | 2 |
| 2026-W41 | 1 | 1 |
In their words
" , " Yes " ), TestCase ( " reason_2 " , " Solve: 2x + 5 = 15 " , " x = 5 " ), # Code Generation TestCase ( " code_1 " , " Write a Python decorator that logs function calls " , None ), TestCase ( " code_2 " , " Fix this bug: [code snippet] " , None ), # Creative Writing TestCase ( " creative_1 " , " Write a haiku about debugging " , None ), TestCase ( " creative_2 " , " Explain quantum computing t
The Broker drops models below a quality floor for the class (raised by complexity or an opus request, lowered by haiku ), then weighs quality, price (input:output blended 3:1) and speed with per-class weights.
Claude Haiku 5.5 came out on 7 October.
Claude Haiku 5.5 API’yi çağırmak için https://api.anthropic.com/v1/messages adresine POST isteği gönderin.
Escada de complexidade e o degrau frontier Dentro das famílias Anthropic e OpenAI há quatro degraus: Complexidade Claude OpenAI Entrada / saída (US$ por milhão) baixa Haiku 5.5 GPT-6 Luna 0,10 / 0,50 nos dois (Haiku até 100K de prompt) média Sonnet 5.5 GPT-5.5 2 / 10 e 5 / 30 alta Opus 5.5 GPT-6.1 Sol 4 / 20 e 2 / 10 frontier Fable 5.1 GPT-6 Astra 10 / 50 nos dois Preços da tabela oficial de cada
Repeated scenes in a shot list, my real failure, are the easy part: the 2B, Opus and Haiku got 13 of 13 lists right.
Brain: Claude (Haiku for normal conversation, a bigger model only for "look at the screen and do it" tasks).
I built a third one, Chisle , and benchmarked all three against Claude with no plugin at all : 20 live tasks, 59+ model runs on Haiku and Sonnet, with the arms differing only in the injected ruleset.