Model Comparison

o1 vs Claude 3.5 SonnetWhich is better in 2026?

o1 shows notably better performance in the majority of benchmarks. Claude 3.5 Sonnet is 4.4x cheaper per token.

Verdict: o1 vs Claude 3.5 Sonnet — which is better?

o1 (by OpenAI) and Claude 3.5 Sonnet (by Anthropic) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

o1 outperforms in 4 benchmarks (GPQA, GSM8k, MATH, MMLU), while Claude 3.5 Sonnet is better at 2 benchmarks (HumanEval, MGSM). o1 shows notably better performance in the majority of benchmarks.

On price, Claude 3.5 Sonnet is roughly 4.4x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Choose o1 if…

  • you want the strongest raw capability — it leads on 4 of 6 shared benchmarks
  • you want the most recent training data — it shipped Dec 2024

Choose Claude 3.5 Sonnet if…

  • cost matters — it's about 4.4x cheaper per token
Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

6 benchmarks

o1 outperforms in 4 benchmarks (GPQA, GSM8k, MATH, MMLU), while Claude 3.5 Sonnet is better at 2 benchmarks (HumanEval, MGSM).

o1 shows notably better performance in the majority of benchmarks.

Wed Jun 17 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Claude 3.5 Sonnet costs less

For input processing, o1 ($15.00/1M tokens) is 5.0x more expensive than Claude 3.5 Sonnet ($3.00/1M tokens).

For output processing, o1 ($60.00/1M tokens) is 4.0x more expensive than Claude 3.5 Sonnet ($15.00/1M tokens).

In conclusion, o1 is more expensive than Claude 3.5 Sonnet.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Wed Jun 17 2026 • llm-stats.com
OpenAI
o1
Input tokens$15.00
Output tokens$60.00
Best providerAzure
Anthropic
Claude 3.5 Sonnet
Input tokens$3.00
Output tokens$15.00
Best providerAWS Bedrock
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Both models have the same input context window of 200,000 tokens. Claude 3.5 Sonnet can generate longer responses up to 200,000 tokens, while o1 is limited to 100,000 tokens.

OpenAI
o1
Input200,000 tokens
Output100,000 tokens
Anthropic
Claude 3.5 Sonnet
Input200,000 tokens
Output200,000 tokens
Wed Jun 17 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Claude 3.5 Sonnet supports multimodal inputs, whereas o1 does not.

Claude 3.5 Sonnet can handle both text and other forms of data like images, making it suitable for multimodal applications.

o1

Text
Images
Audio
Video

Claude 3.5 Sonnet

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

o1

Proprietary

Closed source

Claude 3.5 Sonnet

Proprietary

Closed source

Release Timeline

When each model was launched

o1 was released on 2024-12-17, while Claude 3.5 Sonnet was released on 2024-06-21.

o1 is 6 months newer than Claude 3.5 Sonnet.

o1

Dec 17, 2024

1.5 years ago

5mo newer
Claude 3.5 Sonnet

Jun 21, 2024

2.0 years ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

o1 is available from Azure, OpenAI. Claude 3.5 Sonnet is available from Bedrock, Google.

o1

azure logo
Azure
Input Price:Input: $15.00/1MOutput Price:Output: $60.00/1M
openai logo
OpenAI
Input Price:Input: $15.00/1MOutput Price:Output: $60.00/1M

Claude 3.5 Sonnet

bedrock logo
AWS Bedrock
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
google logo
Google
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

OpenAI
Higher GPQA score (78.0% vs 59.4%)
Higher GSM8k score (97.1% vs 96.4%)
Higher MATH score (96.4% vs 71.1%)
Higher MMLU score (91.8% vs 90.4%)
Anthropic
Supports multimodal inputs
Less expensive input tokens
Less expensive output tokens
Higher HumanEval score (92.0% vs 88.1%)
Higher MGSM score (91.6% vs 89.3%)
OpenAIo1
AnthropicClaude 3.5 Sonnet
Compare in Playground

Detailed Comparison

AI Model Comparison Table
Feature
OpenAI
o1
Anthropic
Claude 3.5 Sonnet

FAQ

Common questions about o1 vs Claude 3.5 Sonnet.

Which is better, o1 or Claude 3.5 Sonnet?

o1 shows notably better performance in the majority of benchmarks. o1 is made by OpenAI and Claude 3.5 Sonnet is made by Anthropic. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does o1 compare to Claude 3.5 Sonnet in benchmarks?

o1 scores GSM8k: 97.1%, MATH: 96.4%, GPQA Physics: 92.8%, MMLU: 91.8%, MGSM: 89.3%. Claude 3.5 Sonnet scores GSM8k: 96.4%, BIG-Bench Hard: 93.1%, HumanEval: 92.0%, MGSM: 91.6%, MMLU: 90.4%.

Is o1 cheaper than Claude 3.5 Sonnet?

Claude 3.5 Sonnet is 5.0x cheaper for input tokens. o1 costs $15.00/M input and $60.00/M output via azure. Claude 3.5 Sonnet costs $3.00/M input and $15.00/M output via bedrock.

What are the context window sizes for o1 and Claude 3.5 Sonnet?

o1 supports 200K tokens and Claude 3.5 Sonnet supports 200K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between o1 and Claude 3.5 Sonnet?

Key differences include input pricing ($15.00 vs $3.00/M), multimodal support (no vs yes). See the full comparison above for benchmark-by-benchmark results.

Who makes o1 and Claude 3.5 Sonnet?

o1 is developed by OpenAI and Claude 3.5 Sonnet is developed by Anthropic.

Related comparisons