Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Anthropic

Claude Haiku Latest

Compatibility alias that routes to the newest version of Claude Haiku. Currently routes to Claude Haiku 5.5 with adaptive thinking.

  • Reasoning
  • Vision
  • Native PDF input
  • Tool Calling
  • Structured Output

Added Mar 29, 2026

Pricing

Auto routing · per 1M tokens
Input
$0.10
Output
$0.50
Cache read
$0.01
Compare provider prices

Specifications

Context window
1M
Max output
128K

Benchmarks

Sourced from LMArena.

Arena Score

1422.4

Overall Rank

#131 / 421

Votes

13,239

Confidence Interval

1416.1 - 1428.7

Category Scores

Coding

#97 / 416

3,132 votes

1489.7

Math

#77 / 404

668 votes

1450.5

Longer Query

#143 / 399

6,005 votes

1421.3

Creative Writing

#169 / 419

3,063 votes

1362.2

Instruction Following

#102 / 421

4,703 votes

1427.5

Hard Prompts

#116 / 421

8,403 votes

1450.8

Additional Categories
21

Korean

#77 / 289

163 votes

1406.0

Industry Mathematical

#93 / 401

729 votes

1450.1

Japanese

#98 / 288

200 votes

1393.2

French

#102 / 301

507 votes

1455.2

Industry Software And It Services

#103 / 421

4,707 votes

1475.6

Expert

#104 / 371

1,272 votes

1463.3

Industry Business And Management And Financial Operations

#118 / 414

2,255 votes

1431.0

Hard Prompts English

#123 / 419

3,234 votes

1456.4

Chinese

#125 / 395

1,090 votes

1462.2

Industry Life And Physical And Social Science

#125 / 419

2,089 votes

1444.8

Polish

#126 / 244

207 votes

1409.5

Exclude Ties

#130 / 421

9,884 votes

1414.5

Spanish

#131 / 303

503 votes

1412.1

English

#132 / 421

4,981 votes

1433.5

Non English

#134 / 421

8,258 votes

1405.7

Multi Turn

#146 / 419

2,064 votes

1414.2

Industry Entertainment And Sports And Media

#147 / 419

3,452 votes

1377.6

Industry Writing And Literature And Language

#147 / 420

3,915 votes

1390.0

Russian

#156 / 385

1,946 votes

1399.9

Industry Legal And Government

#157 / 393

1,032 votes

1410.0

Industry Medicine And Healthcare

#183 / 390

871 votes

1405.6

Published 2026-11-09 · Matched as Claude Haiku 5.5 (High) · CC BY 4.0

LMArena Dataset

Leaderboard results

These leaderboards tested Claude Haiku 5.5, another version of this model.

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 12, 2026

Epoch Capabilities Index

160.4

#17 of 115

FrontierMath v2 (Tiers 1–3)

75.1%

#23 of 83

GPQA Diamond

89.6%

#46 of 119

SimpleQA Verified

23.8%

#70 of 82

FrontierMath v2 (Tier 4)

46.3%

#23 of 67

OTIS Mock AIME 2024–2025

98.9%

#21 of 121

MirrorCode

78.9%

#5 of 39

Chess Puzzles

55.0%

#15 of 82

Mystery Game Puzzles

30.0%

#33 of 77

Filtered and ranked to models on NanoGPT.

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Cache write /M
Auto
Auto
Recommended
$0.10$0.50$0.01$0.125N/AN/A
>100k$0.50$2.50$0.05$0.625
Batch API
ProviderInputOutputCached inputCache write
Anthropic
Anthropicclaude-haiku-5-5
$0.05/M$0.25/M$0.005/M$0.0625/M
>100k$0.25/M$1.25/M$0.025/M$0.313/M

Reliability

Related text models

Compare Claude Haiku Latest with similar models from the same provider or model family.

Claude Haiku 5.5

anthropic/claude-haiku-5.5

Claude Haiku 5.5 is Anthropic's fastest and most capable small model, designed for high-volume, cost-sensitive tasks such as summaries, classification, coding assistance, and live customer support. It delivers major gains over Haiku 4.5 while costing around 75% less to run.

Claude Fable 5.2

anthropic/claude-fable-5.2

Anthropic's Claude Fable 5.2 supports demanding reasoning, coding, and long-running agentic work, with text, image, and PDF inputs, tool calling, and structured outputs. It has a 1M-token context window and up to 128K output tokens. Adaptive thinking is always on, with five effort levels. Prompts and outputs are retained for 30 days; Zero Data Retention is not available.

Claude Sonnet 5.5

anthropic/claude-sonnet-5.5

Claude Sonnet 5.5 handles everyday coding, tool-based workflows, visual analysis, and polished writing with a 1M-token context window. This version skips up-front thinking and can reason between tool calls for faster responses; use Thinking for deeper planning and complex problems.

Claude Sonnet 5.5 Thinking

anthropic/claude-sonnet-5.5:thinking

Claude Sonnet 5.5 with adaptive thinking for complex coding, multi-step tool use, visual analysis, and detailed planning. Supports a 1M-token context window and five reasoning effort levels, with stronger thinking available when a task needs it.

Claude Opus 5.5

anthropic/claude-opus-5.5

Claude Opus 5.5 is Anthropic's flagship model for agentic coding, computer use, complex knowledge work, and long-running tasks, with improved efficiency and more natural communication.

Claude Fable 5.1

anthropic/claude-fable-5.1

Claude Fable 5.1 improves on Fable 5 across agentic coding, long-running workflows, front-end and visual code generation, finance, analysis, and knowledge work, with more concise plans and summaries. Anthropic retains prompts and outputs for 30 days; Zero Data Retention is not available.