#37
Claude Haiku 4.5
claude-haiku-4-5Helpfulness
Instruction
Following
Comprehension
Empathy
Creative
Writing
Helpfulness
0.0
Instruction Following
0.0
Comprehension
0.0
Empathy
0.0
Creative Writing
0.0
Speed
Avg 93 tok/s
Release Date
October 15, 2025
Lab
Anthropic
Type
Proprietary
Context Size
200K
Max Output Tokens
64K
Cost per 1 million tokens
$1.00 / $5.00
Model Inputs*
Text, Images, PDFs
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
85.52 pts
Rank #37
48th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Claude Haiku 4.5 is Anthropic's high-speed, cost-efficient model that delivers near-frontier intelligence while remaining optimized for real-time applications. It provides strong general helpfulness with solid comprehension and instruction-following, making it well-suited for assistants, support workflows, and lightweight coding tasks. The model offers good creative writing ability and handles sensitive conversations with a reasonable degree of empathy, though it prioritizes responsiveness and throughput over the deeper reasoning and nuance found in larger frontier models.
Overall Score vs Price
Price axis is logarithmic (USD per 1M input tokens) · Higher score and lower price is better
Ringed point is this model
Anthropic
DeepSeek
Google
Meta
Moonshot
OpenAI
SpaceX AI
Zhipu AI
Intelligence
Overall Score · Higher is better
Speed
Output tokens per second · Higher is better
Price
USD per 1M input tokens · Lower is better
Anthropic Models
Overall Score · Same provider
Claude Haiku Family
Overall Score · Same model family
Closest Rivals
Overall Score · Nearest by overall rank