मुख्य सामग्री पर जाएं

Claude Haiku 5.5 (Max)

AnthropicClaudeProprietary

विवरण

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`.

रिलीज़ तिथि
2026-10-07
पैरामीटर
—
संदर्भ लंबाई
1.0M
मोडैलिटीज़
image, pdf, text

क्षमता रडार

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

रैंकिंग

बेंचमार्क स्कोर (LLM Stats)

(LLM Stats (zeroeval))

Agents

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

Biology

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

Code

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

General

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

Healthcare

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

Language

MILU87.6%स्वयं

Multimodal

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

Reasoning

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

Science

LatchBio SingleCellBench56.2%स्वयं

Vision

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

AA मूल्यांकन सूचकांक

(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 श्रेणी स्कोर

(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

मूल्य निर्धारण

इनपुट मूल्य$0.1 / 1M टोकन
आउटपुट मूल्य$0.5 / 1M टोकन
मिश्रित मूल्य (3:1)$0.2 / 1M टोकन
कैश पठन मूल्य$0.01 / 1M टोकन
कैश लेखन मूल्य$0.125 / 1M टोकन

गति

टोकन/सेकंड227.9
पहले टोकन में देरी292.43s
पहले उत्तर में देरी292.43s

प्रदाता मूल्य रैंकिंग

प्रदाता मूल्य रैंकिंग

1 प्रदाता

प्रदाताइनपुटआउटपुट
1Anthropic
$0
$0

इस मॉडल के लिए विभिन्न API प्रदाताओं के मूल्य निर्धारण की तुलना करें।

बाहरी लिंक