Claude 3.5 Sonnet vs Claude 3 Opus
Claude 3.5 Sonnet significantly outperforms across most benchmarks. Claude 3.5 Sonnet is 5.0x cheaper per token.
Anthropic · Anthropic · Updated for 2026
Which is better?
Claude 3.5 Sonnet outperforms in 9 benchmarks (BIG-Bench Hard, DROP, GPQA, GSM8k, HumanEval, MATH, MGSM, MMLU, MMLU-Pro), while Claude 3 Opus is better at 0 benchmarks. Claude 3.5 Sonnet significantly outperforms across most benchmarks.
On price, Claude 3.5 Sonnet is roughly 5.0x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Based on current benchmark, pricing, and model metadata for 2026.
Choose Claude 3.5 Sonnet
- you want the strongest raw capability — it leads on 9 of 9 shared benchmarks
- cost matters — it's about 5.0x cheaper per token
- you want the most recent training data — it shipped Jun 2024
Choose Claude 3 Opus
- you want predictable pricing at $15.00/M input and $75.00/M output
At a glance
The differences that matter most.
Performance Benchmarks
Comparative analysis across standard metrics
Claude 3.5 Sonnet outperforms in 9 benchmarks (BIG-Bench Hard, DROP, GPQA, GSM8k, HumanEval, MATH, MGSM, MMLU, MMLU-Pro), while Claude 3 Opus is better at 0 benchmarks.
Claude 3.5 Sonnet significantly outperforms across most benchmarks.
Arena Performance
Playground indexes and blind preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Claude 3.5 Sonnet ($3.00/1M tokens) is 5.0x cheaper than Claude 3 Opus ($15.00/1M tokens).
For output processing, Claude 3.5 Sonnet ($15.00/1M tokens) is 5.0x cheaper than Claude 3 Opus ($75.00/1M tokens).
In conclusion, Claude 3 Opus is more expensive than Claude 3.5 Sonnet.*
* 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
Supported data types and modalities
Both Claude 3.5 Sonnet and Claude 3 Opus support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
Claude 3.5 Sonnet
Claude 3 Opus
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 3.5 Sonnet was released on 2024-06-21, while Claude 3 Opus was released on 2024-02-29.
Claude 3.5 Sonnet is 4 months newer than Claude 3 Opus.
Jun 21, 2024
2.2 years ago
3mo newerFeb 29, 2024
2.5 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 Sonnet is available from Bedrock, Google. Claude 3 Opus is available from Anthropic, Bedrock, Google.
Claude 3.5 Sonnet
Claude 3 Opus
Outputs Comparison
Judge for yourself.
Run your own prompts against Claude 3.5 Sonnet and Claude 3 Opus side-by-side, then vote on the output you prefer.
FAQ
Common questions about Claude 3.5 Sonnet vs Claude 3 Opus.