Skip to main content

Claude Haiku 5.5 (Max)

AnthropicClaudeProprietary

Description

Claude Haiku 5.5 is Anthropic's cheapest, fastest, and most capable small model to date, and the successor to Claude Haiku 4.5. It targets high-volume, cost-sensitive work (summaries, compaction, classification, database queries) and pairs with Opus 5.5 / Sonnet 5.5 as a coding subagent; it is especially strong for speed-sensitive tasks like live support and browser use. It is the first Haiku-class model with adjustable effort (low/medium/high/xhigh/max; Claude Platform default medium). It accepts text and image input (including file/PDF) with text output, supports multilingual and vision workloads, tool use, and adaptive thinking. Context window is 1M tokens with 128K max output; knowledge cutoff is June 2026. Claude Platform pricing is tiered by prompt length: prompts up to 100K tokens are $0.10/$0.50 per million input/output (cache read $0.01, 5m cache write $0.125); prompts over 100K are $0.50/$2.50 (cache read $0.05, 5m cache write $0.625). Catalog provider pricing stores the <=100K tier. Capability scores are self-reported from the Claude Haiku 5.5 System Card (Table 8.1.A and §8) and the launch announcement. Available on the Claude API as `claude-haiku-5-5`.

Release Date
2026-10-07
Parameters
—
Context Length
1.0M
Modalities
image, pdf, text

Capability Radar

44
general
55
coding
50
reasoning
51
science
30
agents
60
multimodal

Rankings

Domain#RankScoreSource
Agentic Capability42
50.0
LS
Code Ranking15
93.0
AA
General Ranking23
74.0
AA
Math Reasoning39
86.0
LB
Multimodal Ranking83
50.0
LS
Reasoning29
85.0
LB
Science49
76.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

AA-Briefcase v1.11578.00 / 3000SR
Program Bench82.0%SR
OfficeQA73.5%SR
OfficeQA Pro60.3%SR

Biology

LatchBio SpatialBench Verified67.7%SR
Protocols Understanding (V2)64.1%SR
Protocols Troubleshooting58.0%SR
Medicinal Chemistry (ADME)58.0%SR
Protein Design — Library Ranking45.3%SR
Biomedical image analysis43.5%SR
Protein Design — Sequence Generation33.1%SR
Morphology-to-molecule matching25.4%SR

Code

BenchCAD (with Python tool)87.0%SR
BenchCAD67.0%SR
FrontierSWE V243.8%SR

General

GDPval-AA 2.11620.00 / 3000SR
Global-MMLU87.8%SR

Healthcare

HealthBench Professional (raw)71.0%SR
HealthBench Professional64.8%SR
HealthBench61.6%SR
PhysicianBench43.0%SR

Language

MILU87.6%SR

Multimodal

OSWorld 2.1 (partial)72.4%SR
OSWorld 2.1 (strict)37.1%SR

Reasoning

SWE-bench Multilingual83.7%SR
SWE-Bench ProPrinceton NLP (2024)64.8%SR
FrontierCode 1.1 (Extended)58.4%SR
Humanity's Last Exam (with tools)57.4%SR
FrontierCode 1.146.4%SR
Humanity's Last Exam (no tools, text-only)45.9%SR
Terminal-Bench 4.039.2%SR
SWE-Bench Multimodal30.7%SR
Terminal-Bench-Science 0.120.6%SR

Science

LatchBio SingleCellBench56.2%SR

Vision

Chartography86.2%SR
Chartography (no tools)46.4%SR

AA Evaluation Indices

(Artificial Analysis)
Lcr(Artificial Analysis)
82.7
Scicode(UIUC + Argonne National Lab (2024))
55.0
Hle(Center for AI Safety + Scale AI (2025))
44.4
Intelligence Index(Artificial Analysis)
43.4
Terminalbench V4 0
32.8

LLM Stats Category Scores

(LLM Stats (zeroeval))
Productivity
100
Agents
100
Reasoning
100
General
100
Language
90
Multimodal
60
Science
60
Healthcare
60
Biology
60
Code
60
Vision
60
Math
50
Tool Calling
30

Pricing

Input Price$0.1 / 1M tokens
Output Price$0.5 / 1M tokens
Blended Price (3:1)$0.2 / 1M tokens
Cache Read Price$0.01 / 1M tokens
Cache Write Price$0.125 / 1M tokens

Speed

Tokens/sec227.9
Time to First Token292.43s
Time to Answer292.43s

Provider Price Ranking

Provider Price Ranking

1 providers

ProviderInputOutput
1Anthropic
$0
$0

Compare pricing across different API providers for this model.

External Sources