Claude Haiku 4.5 vs Claude Sonnet 4
Claude Haiku 4.5 and Claude Sonnet 4 are closely matched at 25.6 and 24.2 on the LLM Stats Score. Claude Haiku 4.5 is 3.0x cheaper per token.
Anthropic · Anthropic · Updated for 2026
Which is better?
Claude Haiku 4.5 and Claude Sonnet 4 are closely matched on the overall LLM Stats Score at 25.6 and 24.2.
In the 5 individual benchmarks reported for both models, Claude Haiku 4.5 wins 3; this is a narrower head-to-head signal than the composite indexes.
On price, Claude Haiku 4.5 is roughly 3.0x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Claude Haiku 4.5
- you value its reported benchmark strengths — it wins 3 of 5 exact shared results
- cost matters — it's about 3.0x cheaper per token
- you want the most recent training data — it shipped Oct 2025
Choose Claude Sonnet 4
- you want predictable pricing at $3.00/M input and $15.00/M output
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
12 reported for Claude Haiku 4.5 · 8 for Claude Sonnet 4
Claude Haiku 4.5 outperforms in 3 benchmarks (AIME 2025, SWE-Bench Verified, Terminal-Bench), while Claude Sonnet 4 is better at 2 benchmarks (GPQA, MMMLU).
Claude Haiku 4.5 has a slight edge in benchmark performance.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Claude Haiku 4.5 ($1.00/1M tokens) is 3.0x cheaper than Claude Sonnet 4 ($3.00/1M tokens).
For output processing, Claude Haiku 4.5 ($5.00/1M tokens) is 3.0x cheaper than Claude Sonnet 4 ($15.00/1M tokens).
In conclusion, Claude Sonnet 4 is more expensive than Claude Haiku 4.5.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
Both models have the same input context window of 200,000 tokens. Both models can generate responses up to 64,000 tokens.
Input capabilities
Documented input modalities across available providers
Both Claude Haiku 4.5 and Claude Sonnet 4 support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
Claude Haiku 4.5
Claude Sonnet 4
License
Usage and distribution terms
Both models are licensed under proprietary licenses.
Both models have usage restrictions defined by their respective organizations.
Proprietary
Closed source
Proprietary
Closed source
Release Timeline
When each model was launched
Claude Haiku 4.5 was released on 2025-10-15, while Claude Sonnet 4 was released on 2025-05-22.
Claude Haiku 4.5 is 5 months newer than Claude Sonnet 4.
Oct 15, 2025
1.0 years ago
4mo newerMay 22, 2025
1.4 years ago
Knowledge Cutoff
When training data ends
Claude Haiku 4.5 has a documented knowledge cutoff of 2025-02-01, while Claude Sonnet 4's cutoff date is not specified.
We can confirm Claude Haiku 4.5's training data extends to 2025-02-01, but cannot make a direct comparison without Claude Sonnet 4's cutoff date.
Feb 2025
—
Provider Availability
Claude Haiku 4.5 is available from Anthropic, DeepInfra, Vertex AI. Claude Sonnet 4 is available from Anthropic, Bedrock, Google.
Claude Haiku 4.5
Claude Sonnet 4
Outputs Comparison
Judge for yourself.
Run your own prompts against Claude Haiku 4.5 and Claude Sonnet 4 side-by-side, then vote on the output you prefer.
FAQ
Common questions about Claude Haiku 4.5 vs Claude Sonnet 4.