The AI arena is free today

Open Superagent

GPT-4o mini vs o1-preview

o1-preview leads the LLM Stats Score 16.8 to 3.9. GPT-4o mini is 100.0x cheaper per token.

OpenAI · OpenAI · Updated for 2026

Which is better?

o1-preview leads the overall LLM Stats Score 16.8 to 3.9, ranking #204 overall.

In the 5 individual benchmarks reported for both models, o1-preview wins 5; this is a narrower head-to-head signal than the composite indexes.

On price, GPT-4o mini is roughly 100.0x 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 GPT-4o mini

  • cost matters — it's about 100.0x cheaper per token

Choose o1-preview

  • overall performance matters — it scores 16.8 and ranks #204 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 5 of 5 exact shared results
  • you want the most recent training data — it shipped Sep 2024

At a glance

The differences that matter most.

Core performance indexes
3.9
#291
16.8
#204
4.3
#282
17.1
#198
-0.4
#232
-2.9
#239
Cost, coverage & limits
Benchmark wins
0 of 5
5 of 5
Input price
$0.15 / M
$15.00 / M
Output price
$0.60 / M
$60.00 / M
Context window
128,000
128,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
GPT-4o mini
o1-preview
11.8#232
20.4#150
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

9 reported for GPT-4o mini · 8 for o1-preview

5 shared

GPT-4o mini outperforms in 0 benchmarks, while o1-preview is better at 5 benchmarks (GPQA, MATH, MGSM, MMLU, SWE-Bench Verified).

o1-preview significantly outperforms across most benchmarks.

Wed Sep 02 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

GPT-4o mini costs less

For input processing, GPT-4o mini ($0.15/1M tokens) is 100.0x cheaper than o1-preview ($15.00/1M tokens).

For output processing, GPT-4o mini ($0.60/1M tokens) is 100.0x cheaper than o1-preview ($60.00/1M tokens).

In conclusion, o1-preview is more expensive than GPT-4o mini.*

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

Lowest available price from all providers
Wed Sep 02 2026 • llm-stats.com
OpenAI
GPT-4o mini
Input tokens$0.15
Output tokens$0.60
Best providerAzure
OpenAI
o1-preview
Input tokens$15.00
Output tokens$60.00
Best providerOpenAI
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 128,000 tokens. o1-preview can generate longer responses up to 32,768 tokens, while GPT-4o mini is limited to 16,384 tokens.

OpenAI
GPT-4o mini
Input128,000 tokens
Output16,384 tokens
OpenAI
o1-preview
Input128,000 tokens
Output32,768 tokens
Wed Sep 02 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

GPT-4o mini supports multimodal inputs, whereas o1-preview does not.

GPT-4o mini can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-4o mini

Text
Images
Audio
Video

o1-preview

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.

GPT-4o mini

Proprietary

Closed source

o1-preview

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-4o mini was released on 2024-07-18, while o1-preview was released on 2024-09-12.

o1-preview is 2 months newer than GPT-4o mini.

GPT-4o mini

Jul 18, 2024

2.1 years ago

o1-preview

Sep 12, 2024

2.0 years ago

1mo newer

Knowledge Cutoff

When training data ends

GPT-4o mini has a documented knowledge cutoff of 2023-10-01, while o1-preview's cutoff date is not specified.

We can confirm GPT-4o mini's training data extends to 2023-10-01, but cannot make a direct comparison without o1-preview's cutoff date.

GPT-4o mini

Oct 2023

o1-preview

Provider Availability

GPT-4o mini is available from Azure. o1-preview is available from OpenAI, Azure.

GPT-4o mini

azure logo
Azure
Input Price:Input: $0.15/1MOutput Price:Output: $0.60/1M

o1-preview

openai logo
OpenAI
Input Price:Input: $15.00/1MOutput Price:Output: $60.00/1M
azure logo
Azure
Input Price:Input: $16.50/1MOutput Price:Output: $66.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against GPT-4o mini and o1-preview side-by-side, then vote on the output you prefer.

GPT-4o mini
✓ Preferred
o1-preview
Open in Playground

FAQ

Common questions about GPT-4o mini vs o1-preview.

Which is better, GPT-4o mini or o1-preview?

o1-preview leads the LLM Stats Score 16.8 to 3.9. GPT-4o mini is made by OpenAI and o1-preview is made by OpenAI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does GPT-4o mini compare to o1-preview in benchmarks?

GPT-4o mini scores HumanEval: 87.2%, MGSM: 87.0%, MMLU: 82.0%, DROP: 79.7%, MATH: 70.2%. o1-preview scores MGSM: 90.8%, MMLU: 90.8%, MATH: 85.5%, GPQA: 73.3%, LiveBench: 52.3%.

Is GPT-4o mini cheaper than o1-preview?

GPT-4o mini is 100.0x cheaper for input tokens. GPT-4o mini costs $0.15/M input and $0.60/M output via azure. o1-preview costs $15.00/M input and $60.00/M output via openai.

What are the context window sizes for GPT-4o mini and o1-preview?

GPT-4o mini supports 128K tokens and o1-preview supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between GPT-4o mini and o1-preview?

Key differences include LLM Stats Score (3.9 vs 16.8), input pricing ($0.15 vs $15.00/M), multimodal support (yes vs no). See the full comparison above for benchmark-by-benchmark results.