Claude Haiku 4.5
Parameters
Undisclosed
Context Length
200K
Modality
Text
Architecture
Undisclosed
License
Proprietary
Release Date
1 Oct 2025
Knowledge Cutoff
Feb 2025
API Pricing (per 1M)
Input: $1.00 · Output: $5.00
Evaluation Benchmarks
Rank
#138
| Benchmark | Score | Rank |
|---|---|---|
Software Engineering | 0.67 | 19 |
StackUnseen | 0.476 | 25 |
Data Analysis | 0.59 | 59 |
General | 0.46 | 63 |
Reasoning | 0.62 | 63 |
LiveBench Average | 0.46 | 63 |
Coding | 0.48 | 64 |
Graduate-Level QA | 0.73 | 80 |
Agentic Index | 0.08 | 96 |
Coding Index | auto 0.44 | 102 |
Web Development | 1330 | 103 |
General Text | 1414 | 106 |
Intelligence Index | auto 0.17 Standard 0.15 | 210 221 |
Rankings
Overall Rank
#138
Coding Rank
#96
About Claude Haiku 4.5
Claude Haiku 4.5 is Anthropic's high-throughput multimodal model engineered for low-latency subagent execution and real-time workflows. It combines rapid inference with extended thinking capabilities across a 200K token context window.
Technical Specifications
Architecture specifications are undisclosed for proprietary models.
Resources
About Claude 4.5
Enhanced Claude models with further improvements in reasoning, coding, and agentic capabilities. Features advanced thinking modes with adjustable effort levels (high, medium, standard) for optimal performance-latency tradeoffs. Excels at complex analysis, software development, web development, and long-context understanding. Includes thinking variants that expose reasoning process for improved transparency.