Claude 3.5 Haiku vs Claude 3.5 Sonnet
Claude 3.5 Sonnet leads the LLM Stats Score 19.3 to 5.4. Claude 3.5 Haiku is 3.8x cheaper per token.
Anthropic · Anthropic · Updated for 2026
Which is better?
Claude 3.5 Sonnet leads the overall LLM Stats Score 19.3 to 5.4, ranking #192 overall.
In the 9 individual benchmarks reported for both models, Claude 3.5 Sonnet wins 9; this is a narrower head-to-head signal than the composite indexes.
On price, Claude 3.5 Haiku is roughly 3.8x 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 3.5 Haiku
- cost matters — it's about 3.8x cheaper per token
Choose Claude 3.5 Sonnet
- overall performance matters — it scores 19.3 and ranks #192 on LLM Stats
- your work emphasizes reasoning — it leads those capability indexes
- you value its reported benchmark strengths — it wins 9 of 9 exact shared results
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
9 reported for Claude 3.5 Haiku · 19 for Claude 3.5 Sonnet
Claude 3.5 Haiku outperforms in 0 benchmarks, while Claude 3.5 Sonnet is better at 9 benchmarks (DROP, GPQA, HumanEval, MATH, MGSM, MMLU-Pro, SWE-Bench Verified, TAU-bench Airline, TAU-bench Retail).
Claude 3.5 Sonnet significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Claude 3.5 Haiku ($0.80/1M tokens) is 3.8x cheaper than Claude 3.5 Sonnet ($3.00/1M tokens).
For output processing, Claude 3.5 Haiku ($4.00/1M tokens) is 3.8x cheaper than Claude 3.5 Sonnet ($15.00/1M tokens).
In conclusion, Claude 3.5 Sonnet is more expensive than Claude 3.5 Haiku.*
* 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 200,000 tokens.
Input capabilities
Documented input modalities across available providers
Claude 3.5 Sonnet supports multimodal inputs, whereas Claude 3.5 Haiku does not.
Claude 3.5 Sonnet can handle both text and other forms of data like images, making it suitable for multimodal applications.
Claude 3.5 Haiku
Claude 3.5 Sonnet
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
Both models were released on 2024-10-22.
They likely represent similar generations of model development.
Oct 22, 2024
1.9 years ago
Oct 22, 2024
1.9 years ago
Knowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Claude 3.5 Haiku is available from Bedrock, Google, Anthropic. Claude 3.5 Sonnet is available from Anthropic, Bedrock, Google.
Claude 3.5 Haiku
Claude 3.5 Sonnet
Outputs Comparison
Judge for yourself.
Run your own prompts against Claude 3.5 Haiku and Claude 3.5 Sonnet side-by-side, then vote on the output you prefer.
FAQ
Common questions about Claude 3.5 Haiku vs Claude 3.5 Sonnet.