DataLearner logoDataLearnerAI
Latest AI Insights
Model Leaderboards
Benchmarks
Model Directory
Model Comparison
Resource Center
Tools
LanguageEnglish
DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

Products

  • Leaderboards
  • Model comparison
  • Datasets

Resources

  • Tutorials
  • Editorial
  • Tool directory

Company

  • About
  • Privacy policy
  • Data methodology
  • Contact

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

Privacy policyTerms of service
Page navigation
Page navigation
Model catalogHaiku 4.5
HA

Haiku 4.5

Multimodal model

Claude Haiku 4.5

Release date: 2025-10-15Updated: 2025-10-19 22:16:181,357
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
200K (204800)
Chinese support
Supported
Reasoning ability

Claude Haiku 4.5 is an AI model published by Anthropic, released on 2025-10-15, for Multimodal model, and 200K tokens context length, with no open-source license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Haiku 4.5

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
200K (204800) tokens
Max output length
64K (65536) tokens
Model type
Multimodal model
Release date
2025-10-15
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Haiku 4.5

Open source & experience

Code license
Not open source
Weights license
Not open source
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
https://claude.ai
Haiku 4.5

Official resources

Paper
Introducing Claude Haiku 4.5
DataLearnerAI blog
DataLearnerAI blog
Haiku 4.5

API details

API speed
5/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard pricingStandard
ModalityInputOutput
Text$1$5
Image$1--
Cached pricingCache
ModalityInput cacheOutput cache
Text$1.25$0.10
Image$1.25--
Haiku 4.5

Benchmark Results

Haiku 4.5 currently shows benchmark results led by AIME2025 (20 / 106, score 96.30), Terminal-Bench (11 / 35, score 41), LiveBench (17 / 52, score 71.38). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

12 evaluations
Benchmark / mode
Score
Rank/total
MMLU Pro
Standard Mode
76
78 / 126
MMLU Pro
Extended
80
60 / 126
GPQA Diamond
Standard Mode
60.50
137 / 177
GPQA Diamond
Extended
73.30
99 / 177
LiveBench
Standard Mode
60.42
42 / 52
LiveBench
Extended
71.38
17 / 52
ARC-AGI
Standard Mode
14.30
56 / 65
ARC-AGI
Extended
47.70
43 / 65
HLE
Standard Mode
4.30
152 / 154
HLE
Extended
9.70
130 / 154
ARC-AGI-2
Standard Mode
1.30
52 / 59
ARC-AGI-2
Extended
4.50
47 / 59

Coding and Software Engineer

5 evaluations
Benchmark / mode
Score
Rank/total
SWE-bench Verified
Standard ModeTools
60.60
73 / 105
SWE-bench Verified
128KTools
73.30
41 / 105
LiveCodeBench
Standard Mode
51
91 / 120
LiveCodeBench
Extended
62
67 / 120
SWE-Bench Pro - Public
ExtendedTools
39.45
37 / 40

Math and Reasoning

5 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Standard Mode
39
94 / 106
AIME2025
128K
80.70
57 / 106
AIME2025
128KTools
96.30
20 / 106
FrontierMath
Standard Mode
4.10
41 / 60
FrontierMath - Tier 4
32K
2.10
56 / 80

AI Agent - Tool Usage

2 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench
Standard ModeTools
26
26 / 35
Terminal-Bench
32KTools
41
11 / 35

Multimodal Understanding

1 evaluations
Benchmark / mode
Score
Rank/total
MMMU
128K
73.20
19 / 28

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench
Standard ModeTools
33
40 / 40

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Extended
54.30
25 / 29

Claw-style Agent Evaluation

2 evaluations
Benchmark / mode
Score
Rank/total
Claw Bench
Thinking ModeTools
89.40
11 / 29
Pinch Bench
Thinking ModeTools
82
21 / 37
View benchmark analysisCompare with other models

Compare with other models

  • Peer modelHaiku 4.5 vs Gemini 3.0 Flash10 benchmarks
  • Peer modelHaiku 4.5 vs GPT-5.4 mini5 benchmarks
  • Earlier versionHaiku 4.5 vs Claude 3.5 Haiku3 benchmarks

Want a custom combination? Open the compare tool

Haiku 4.5

Publisher

Anthropic
Anthropic
View publisher details
Claude Haiku 4.5

Model Overview

Claude Haiku 4.5 is an AI model published by Anthropic, released on 2025-10-15, for Multimodal model, and 200K tokens context length, with no open-source license.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code