Model Comparison

o1 vs DeepSeek-R1-0528

DeepSeek-R1-0528 significantly outperforms across most benchmarks. DeepSeek-R1-0528 is 28.8x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

4 benchmarks

o1 outperforms in 0 benchmarks, while DeepSeek-R1-0528 is better at 4 benchmarks (AIME 2024, GPQA, SimpleQA, SWE-Bench Verified).

DeepSeek-R1-0528 significantly outperforms across most benchmarks.

Thu Apr 16 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

DeepSeek-R1-0528 costs less

For input processing, o1 ($15.00/1M tokens) is 30.0x more expensive than DeepSeek-R1-0528 ($0.50/1M tokens).

For output processing, o1 ($60.00/1M tokens) is 27.9x more expensive than DeepSeek-R1-0528 ($2.15/1M tokens).

In conclusion, o1 is more expensive than DeepSeek-R1-0528.*

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

Lowest available price from all providers
Thu Apr 16 2026 • llm-stats.com
OpenAI
o1
Input tokens$15.00
Output tokens$60.00
Best providerAzure
DeepSeek
DeepSeek-R1-0528
Input tokens$0.50
Output tokens$2.15
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

o1 accepts 200,000 input tokens compared to DeepSeek-R1-0528's 131,072 tokens. DeepSeek-R1-0528 can generate longer responses up to 131,072 tokens, while o1 is limited to 100,000 tokens.

OpenAI
o1
Input200,000 tokens
Output100,000 tokens
DeepSeek
DeepSeek-R1-0528
Input131,072 tokens
Output131,072 tokens
Thu Apr 16 2026 • llm-stats.com

License

Usage and distribution terms

o1 is licensed under a proprietary license, while DeepSeek-R1-0528 uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

o1

Proprietary

Closed source

DeepSeek-R1-0528

MIT

Open weights

Release Timeline

When each model was launched

o1 was released on 2024-12-17, while DeepSeek-R1-0528 was released on 2025-05-28.

DeepSeek-R1-0528 is 5 months newer than o1.

o1

Dec 17, 2024

1.3 years ago

DeepSeek-R1-0528

May 28, 2025

10 months ago

5mo newer

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. DeepSeek-R1-0528 is available from DeepInfra, DeepSeek, Novita.

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

DeepSeek-R1-0528

deepinfra logo
Deepinfra
Input Price:Input: $0.50/1MOutput Price:Output: $2.15/1M
deepseek logo
DeepSeek
Input Price:Input: $0.55/1MOutput Price:Output: $2.19/1M
novita logo
Novita
Input Price:Input: $0.70/1MOutput Price:Output: $2.50/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

OpenAI
Larger context window (200,000 tokens)
DeepSeek
Less expensive input tokens
Less expensive output tokens
Has open weights
Higher AIME 2024 score (91.4% vs 74.3%)
Higher GPQA score (81.0% vs 78.0%)
Higher SimpleQA score (92.3% vs 47.0%)
Higher SWE-Bench Verified score (44.6% vs 41.0%)

Detailed Comparison

AI Model Comparison Table
Feature
OpenAI
o1
DeepSeek
DeepSeek-R1-0528

FAQ

Common questions about o1 vs DeepSeek-R1-0528

DeepSeek-R1-0528 significantly outperforms across most benchmarks. o1 is made by OpenAI and DeepSeek-R1-0528 is made by DeepSeek. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
o1 scores GSM8k: 97.1%, MATH: 96.4%, GPQA Physics: 92.8%, MMLU: 91.8%, MGSM: 89.3%. DeepSeek-R1-0528 scores MMLU-Redux: 93.4%, SimpleQA: 92.3%, AIME 2024: 91.4%, AIME 2025: 87.5%, MMLU-Pro: 85.0%.
DeepSeek-R1-0528 is 30.0x cheaper for input tokens. o1 costs $15.00/M input and $60.00/M output via azure. DeepSeek-R1-0528 costs $0.50/M input and $2.15/M output via deepinfra.
o1 supports 200K tokens and DeepSeek-R1-0528 supports 131K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (200K vs 131K), input pricing ($15.00 vs $0.50/M), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.
o1 is developed by OpenAI and DeepSeek-R1-0528 is developed by DeepSeek.