DeepSeek-R1-0528 vs DeepSeek-V3 0324
DeepSeek-R1-0528 leads the LLM Stats Score 24.1 to 13.4. DeepSeek-V3 0324 is 2.3x cheaper per token.
DeepSeek · DeepSeek · Updated for 2026
Which is better?
DeepSeek-R1-0528 leads the overall LLM Stats Score 24.1 to 13.4, ranking #166 overall.
In the 4 individual benchmarks reported for both models, DeepSeek-R1-0528 wins 4; this is a narrower head-to-head signal than the composite indexes.
On price, DeepSeek-V3 0324 is roughly 2.3x 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 DeepSeek-R1-0528
- overall performance matters — it scores 24.1 and ranks #166 on LLM Stats
- your work emphasizes reasoning — it leads those capability indexes
- you value its reported benchmark strengths — it wins 4 of 4 exact shared results
- you want the most recent training data — it shipped May 2025
Choose DeepSeek-V3 0324
- cost matters — it's about 2.3x cheaper per token
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
16 reported for DeepSeek-R1-0528 · 5 for DeepSeek-V3 0324
DeepSeek-R1-0528 outperforms in 4 benchmarks (AIME 2024, GPQA, LiveCodeBench, MMLU-Pro), while DeepSeek-V3 0324 is better at 0 benchmarks.
DeepSeek-R1-0528 significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, DeepSeek-R1-0528 ($0.50/1M tokens) is 2.1x more expensive than DeepSeek-V3 0324 ($0.24/1M tokens).
For output processing, DeepSeek-R1-0528 ($2.15/1M tokens) is 2.4x more expensive than DeepSeek-V3 0324 ($0.90/1M tokens).
In conclusion, DeepSeek-R1-0528 is more expensive than DeepSeek-V3 0324.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
DeepSeek-V3 0324 has 0.0B more parameters than DeepSeek-R1-0528, making it 0.0% larger.
Context Window
Maximum input and output token capacity
Both models have the same input context window of 163,840 tokens. Both models can generate responses up to 163,840 tokens.
License
Usage and distribution terms
DeepSeek-R1-0528 is licensed under MIT, while DeepSeek-V3 0324 uses MIT + Model License (Commercial use allowed).
License differences may affect how you can use these models in commercial or open-source projects.
MIT
Open weights
MIT + Model License (Commercial use allowed)
Open weights
Release Timeline
When each model was launched
DeepSeek-R1-0528 was released on 2025-05-28, while DeepSeek-V3 0324 was released on 2025-03-25.
DeepSeek-R1-0528 is 2 months newer than DeepSeek-V3 0324.
May 28, 2025
1.3 years ago
2mo newerMar 25, 2025
1.5 years ago
Knowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
DeepSeek-R1-0528 is available from DeepInfra, DeepSeek, Novita. DeepSeek-V3 0324 is available from DeepInfra, Novita.
DeepSeek-R1-0528
DeepSeek-V3 0324
Outputs Comparison
Judge for yourself.
Run your own prompts against DeepSeek-R1-0528 and DeepSeek-V3 0324 side-by-side, then vote on the output you prefer.
FAQ
Common questions about DeepSeek-R1-0528 vs DeepSeek-V3 0324.