The AI arena is free today

Open Superagent

DeepSeek R1 Zero vs o1

DeepSeek R1 Zero and o1 are closely matched at 16.0 and 20.9 on the LLM Stats Score.

DeepSeek · OpenAI · Updated for 2026

Which is better?

DeepSeek R1 Zero and o1 are closely matched on the overall LLM Stats Score at 16.0 and 20.9.

The models split the 2 individual benchmarks reported for both models evenly.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose DeepSeek R1 Zero

  • you want the most recent training data — it shipped Jan 2025
  • you need open weights you can self-host or fine-tune

Choose o1

  • you want predictable pricing at $15.00/M input and $60.00/M output

At a glance

The differences that matter most.

Core performance indexes
16.0
#226
20.9
#191
16.3
#216
21.3
#181
4.3
#209
4.6
#206
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
— / M
$15.00 / M
Output price
— / M
$60.00 / M
Context window
200,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
DeepSeek R1 Zero
o1
17.5#194
24.0#121
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

4 reported for DeepSeek R1 Zero · 19 for o1

2 shared

DeepSeek R1 Zero outperforms in 1 benchmarks (AIME 2024), while o1 is better at 1 benchmark (GPQA).

Both models are evenly matched across the benchmarks.

Tue Sep 15 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only o1 specifies input context (200,000 tokens). Only o1 specifies output context (100,000 tokens).

DeepSeek
DeepSeek R1 Zero
Input- tokens
Output- tokens
OpenAI
o1
Input200,000 tokens
Output100,000 tokens
Tue Sep 15 2026 • llm-stats.com

License

Usage and distribution terms

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

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

DeepSeek R1 Zero

MIT

Open weights

o1

Proprietary

Closed source

Release Timeline

When each model was launched

DeepSeek R1 Zero was released on 2025-01-20, while o1 was released on 2024-12-17.

DeepSeek R1 Zero is 1 month newer than o1.

DeepSeek R1 Zero

Jan 20, 2025

1.7 years ago

1mo newer
o1

Dec 17, 2024

1.7 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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against DeepSeek R1 Zero and o1 side-by-side, then vote on the output you prefer.

DeepSeek R1 Zero
✓ Preferred
o1
Open in Playground

FAQ

Common questions about DeepSeek R1 Zero vs o1.

Which is better, DeepSeek R1 Zero or o1?

DeepSeek R1 Zero and o1 are closely matched on the LLM Stats Score at 16.0 and 20.9. DeepSeek R1 Zero is made by DeepSeek and o1 is made by OpenAI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does DeepSeek R1 Zero compare to o1 in benchmarks?

DeepSeek R1 Zero scores MATH-500: 95.9%, AIME 2024: 86.7%, GPQA: 73.3%, LiveCodeBench: 50.0%. o1 scores GSM8k: 97.1%, MATH: 96.4%, GPQA Physics: 92.8%, MMLU: 91.8%, MGSM: 89.3%.

What are the context window sizes for DeepSeek R1 Zero and o1?

DeepSeek R1 Zero supports an unknown number of tokens and o1 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 DeepSeek R1 Zero and o1?

Key differences include LLM Stats Score (16.0 vs 20.9), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek R1 Zero and o1?

DeepSeek R1 Zero is developed by DeepSeek and o1 is developed by OpenAI.