Model Comparison
o1 vs o1-preview
o1 shows notably better performance in the majority of benchmarks. o1 and o1-preview cost the same.
Performance Benchmarks
Comparative analysis across standard metrics
o1 outperforms in 6 benchmarks (AIME 2024, GPQA, LiveBench, MATH, MMLU, SimpleQA), while o1-preview is better at 2 benchmarks (MGSM, SWE-Bench Verified).
o1 shows notably better performance in the majority of benchmarks.
Arena Performance
Human preference votes
Pricing Analysis
Price comparison per million tokens
For input processing, o1 ($15.00/1M tokens) costs the same as o1-preview ($15.00/1M tokens).
For output processing, o1 ($60.00/1M tokens) costs the same as o1-preview ($60.00/1M tokens).
In conclusion, o1 and o1-preview cost the same.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
o1 accepts 200,000 input tokens compared to o1-preview's 128,000 tokens. o1 can generate longer responses up to 100,000 tokens, while o1-preview is limited to 32,768 tokens.
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
o1 was released on 2024-12-17, while o1-preview was released on 2024-09-12.
o1 is 3 months newer than o1-preview.
Dec 17, 2024
1.4 years ago
3mo newerSep 12, 2024
1.6 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
o1 is available from Azure, OpenAI. o1-preview is available from OpenAI, Azure.
o1
o1-preview
Outputs Comparison
Key Takeaways
o1
View detailsOpenAI
o1-preview
View detailsOpenAI
Detailed Comparison
| Feature | | |
|---|
FAQ
Common questions about o1 vs o1-preview.