Model Comparison

DeepSeek-R1-0528 vs DeepSeek-V3.2 (Thinking)

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks. DeepSeek-V3.2 (Thinking) is 2.9x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

11 benchmarks

DeepSeek-R1-0528 outperforms in 0 benchmarks, while DeepSeek-V3.2 (Thinking) is better at 10 benchmarks (AIME 2025, BrowseComp, BrowseComp-zh, CodeForces, GPQA, HMMT 2025, Humanity's Last Exam, LiveCodeBench, SWE-bench Multilingual, SWE-Bench Verified).

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

Sun May 10 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

DeepSeek-V3.2 (Thinking) costs less

For input processing, DeepSeek-R1-0528 ($0.50/1M tokens) is 1.8x more expensive than DeepSeek-V3.2 (Thinking) ($0.28/1M tokens).

For output processing, DeepSeek-R1-0528 ($2.15/1M tokens) is 5.1x more expensive than DeepSeek-V3.2 (Thinking) ($0.42/1M tokens).

In conclusion, DeepSeek-R1-0528 is more expensive than DeepSeek-V3.2 (Thinking).*

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

Lowest available price from all providers
Sun May 10 2026 • llm-stats.com
DeepSeek
DeepSeek-R1-0528
Input tokens$0.50
Output tokens$2.15
Best providerDeepinfra
DeepSeek
DeepSeek-V3.2 (Thinking)
Input tokens$0.28
Output tokens$0.42
Best providerDeepSeek
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

14.0B diff

DeepSeek-V3.2 (Thinking) has 14.0B more parameters than DeepSeek-R1-0528, making it 2.1% larger.

DeepSeek
DeepSeek-R1-0528
671.0Bparameters
DeepSeek
DeepSeek-V3.2 (Thinking)
685.0Bparameters
671.0B
DeepSeek-R1-0528
685.0B
DeepSeek-V3.2 (Thinking)

Context Window

Maximum input and output token capacity

Both models have the same input context window of 131,072 tokens. DeepSeek-R1-0528 can generate longer responses up to 131,072 tokens, while DeepSeek-V3.2 (Thinking) is limited to 65,536 tokens.

DeepSeek
DeepSeek-R1-0528
Input131,072 tokens
Output131,072 tokens
DeepSeek
DeepSeek-V3.2 (Thinking)
Input131,072 tokens
Output65,536 tokens
Sun May 10 2026 • llm-stats.com

License

Usage and distribution terms

Both models are licensed under MIT.

Both models share the same licensing terms, providing consistent usage rights.

DeepSeek-R1-0528

MIT

Open weights

DeepSeek-V3.2 (Thinking)

MIT

Open weights

Release Timeline

When each model was launched

DeepSeek-R1-0528 was released on 2025-05-28, while DeepSeek-V3.2 (Thinking) was released on 2025-12-01.

DeepSeek-V3.2 (Thinking) is 6 months newer than DeepSeek-R1-0528.

DeepSeek-R1-0528

May 28, 2025

11 months ago

DeepSeek-V3.2 (Thinking)

Dec 1, 2025

5 months ago

6mo 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

DeepSeek-R1-0528 is available from DeepInfra, DeepSeek, Novita. DeepSeek-V3.2 (Thinking) is available from DeepSeek.

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

DeepSeek-V3.2 (Thinking)

deepseek logo
DeepSeek
Input Price:Input: $0.28/1MOutput Price:Output: $0.42/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

DeepSeek

No standout differentiators in the data we have for this pair.

DeepSeek
Less expensive input tokens
Less expensive output tokens
Higher AIME 2025 score (93.1% vs 87.5%)
Higher BrowseComp score (51.4% vs 8.9%)
Higher BrowseComp-zh score (65.0% vs 35.7%)
Higher CodeForces score (79.5% vs 64.3%)
Higher GPQA score (82.4% vs 81.0%)
Higher HMMT 2025 score (90.2% vs 79.4%)
Higher Humanity's Last Exam score (25.1% vs 17.7%)
Higher LiveCodeBench score (83.3% vs 73.3%)
Higher SWE-bench Multilingual score (70.2% vs 30.5%)
Higher SWE-Bench Verified score (73.1% vs 44.6%)

Detailed Comparison

AI Model Comparison Table
Feature
DeepSeek
DeepSeek-R1-0528
DeepSeek
DeepSeek-V3.2 (Thinking)

FAQ

Common questions about DeepSeek-R1-0528 vs DeepSeek-V3.2 (Thinking).

Which is better, DeepSeek-R1-0528 or DeepSeek-V3.2 (Thinking)?

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks. DeepSeek-R1-0528 is made by DeepSeek and DeepSeek-V3.2 (Thinking) is made by DeepSeek. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does DeepSeek-R1-0528 compare to DeepSeek-V3.2 (Thinking) in benchmarks?

DeepSeek-R1-0528 scores MMLU-Redux: 93.4%, SimpleQA: 92.3%, AIME 2024: 91.4%, AIME 2025: 87.5%, MMLU-Pro: 85.0%. DeepSeek-V3.2 (Thinking) scores AIME 2025: 93.1%, HMMT 2025: 90.2%, MMLU-Pro: 85.0%, LiveCodeBench: 83.3%, GPQA: 82.4%.

Is DeepSeek-R1-0528 cheaper than DeepSeek-V3.2 (Thinking)?

DeepSeek-V3.2 (Thinking) is 1.8x cheaper for input tokens. DeepSeek-R1-0528 costs $0.50/M input and $2.15/M output via deepinfra. DeepSeek-V3.2 (Thinking) costs $0.28/M input and $0.42/M output via deepseek.

What are the context window sizes for DeepSeek-R1-0528 and DeepSeek-V3.2 (Thinking)?

DeepSeek-R1-0528 supports 131K tokens and DeepSeek-V3.2 (Thinking) supports 131K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DeepSeek-R1-0528 and DeepSeek-V3.2 (Thinking)?

Key differences include input pricing ($0.50 vs $0.28/M). See the full comparison above for benchmark-by-benchmark results.