The AI arena is free today

Open Superagent

DeepSeek-V3.2 (Thinking) vs o1-preview

DeepSeek-V3.2 (Thinking) leads the LLM Stats Score 32.6 to 16.6. DeepSeek-V3.2 (Thinking) is 83.3x cheaper per token.

DeepSeek · OpenAI · Updated for 2026

Which is better?

DeepSeek-V3.2 (Thinking) leads the overall LLM Stats Score 32.6 to 16.6, ranking #110 overall.

In the 2 individual benchmarks reported for both models, DeepSeek-V3.2 (Thinking) wins 2; this is a narrower head-to-head signal than the composite indexes.

On price, DeepSeek-V3.2 (Thinking) is roughly 83.3x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

DeepSeek-V3.2 (Thinking) also accepts a larger context window (131,072 input tokens), making it the stronger choice for long documents and large codebases.

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

Choose DeepSeek-V3.2 (Thinking)

  • overall performance matters — it scores 32.6 and ranks #110 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results
  • cost matters — it's about 83.3x cheaper per token
  • you process long inputs — it offers a 131,072 token context window
  • you want the most recent training data — it shipped Dec 2025
  • you need open weights you can self-host or fine-tune

Choose o1-preview

  • 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
32.6
#110
16.6
#226
32.6
#107
16.8
#219
22.8
#85
-3.2
#258
Cost, coverage & limits
Benchmark wins
2 of 2
0 of 2
Input price
$0.28 / M
$15.00 / M
Output price
$0.42 / M
$60.00 / M
Context window
131,072
128,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
DeepSeek-V3.2 (Thinking)
o1-preview
30.2#78
20.2#162
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

14 reported for DeepSeek-V3.2 (Thinking) · 8 for o1-preview

2 shared

DeepSeek-V3.2 (Thinking) outperforms in 2 benchmarks (GPQA, SWE-Bench Verified), while o1-preview is better at 0 benchmarks.

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks.

Wed Sep 23 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

DeepSeek-V3.2 (Thinking) costs less

For input processing, DeepSeek-V3.2 (Thinking) ($0.28/1M tokens) is 53.6x cheaper than o1-preview ($15.00/1M tokens).

For output processing, DeepSeek-V3.2 (Thinking) ($0.42/1M tokens) is 142.9x cheaper than o1-preview ($60.00/1M tokens).

In conclusion, o1-preview is more expensive than DeepSeek-V3.2 (Thinking).*

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

Lowest available price from all providers
Wed Sep 23 2026 • llm-stats.com
DeepSeek
DeepSeek-V3.2 (Thinking)
Input tokens$0.28
Output tokens$0.42
Best providerDeepSeek
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

DeepSeek-V3.2 (Thinking) accepts 131,072 input tokens compared to o1-preview's 128,000 tokens. DeepSeek-V3.2 (Thinking) can generate longer responses up to 65,536 tokens, while o1-preview is limited to 32,768 tokens.

DeepSeek
DeepSeek-V3.2 (Thinking)
Input131,072 tokens
Output65,536 tokens
OpenAI
o1-preview
Input128,000 tokens
Output32,768 tokens
Wed Sep 23 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V3.2 (Thinking) is licensed under MIT, while o1-preview uses a proprietary license.

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

DeepSeek-V3.2 (Thinking)

MIT

Open weights

o1-preview

Proprietary

Closed source

Release Timeline

When each model was launched

DeepSeek-V3.2 (Thinking) was released on 2025-12-01, while o1-preview was released on 2024-09-12.

DeepSeek-V3.2 (Thinking) is 15 months newer than o1-preview.

DeepSeek-V3.2 (Thinking)

Dec 1, 2025

9 months ago

1.2yr newer
o1-preview

Sep 12, 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

DeepSeek-V3.2 (Thinking) is available from DeepSeek. o1-preview is available from OpenAI, Azure.

DeepSeek-V3.2 (Thinking)

deepseek logo
DeepSeek
Input Price:Input: $0.28/1MOutput Price:Output: $0.42/1M

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 DeepSeek-V3.2 (Thinking) and o1-preview side-by-side, then vote on the output you prefer.

DeepSeek-V3.2 (Thinking)
✓ Preferred
o1-preview
Open in Playground

FAQ

Common questions about DeepSeek-V3.2 (Thinking) vs o1-preview.

Which is better, DeepSeek-V3.2 (Thinking) or o1-preview?

DeepSeek-V3.2 (Thinking) leads the LLM Stats Score 32.6 to 16.6. DeepSeek-V3.2 (Thinking) is made by DeepSeek 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 DeepSeek-V3.2 (Thinking) compare to o1-preview in benchmarks?

DeepSeek-V3.2 (Thinking) scores AIME 2025: 93.1%, HMMT 2025: 90.2%, MMLU-Pro: 85.0%, LiveCodeBench: 83.3%, GPQA: 82.4%. o1-preview scores MGSM: 90.8%, MMLU: 90.8%, MATH: 85.5%, GPQA: 73.3%, LiveBench: 52.3%.

Is DeepSeek-V3.2 (Thinking) cheaper than o1-preview?

DeepSeek-V3.2 (Thinking) is 53.6x cheaper for input tokens. DeepSeek-V3.2 (Thinking) costs $0.28/M input and $0.42/M output via deepseek. o1-preview costs $15.00/M input and $60.00/M output via openai.

What are the context window sizes for DeepSeek-V3.2 (Thinking) and o1-preview?

DeepSeek-V3.2 (Thinking) supports 131K 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 DeepSeek-V3.2 (Thinking) and o1-preview?

Key differences include LLM Stats Score (32.6 vs 16.6), context window (131K vs 128K), input pricing ($0.28 vs $15.00/M), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V3.2 (Thinking) and o1-preview?

DeepSeek-V3.2 (Thinking) is developed by DeepSeek and o1-preview is developed by OpenAI.