← Back to all providers
D

DeepSeek

DeepSeek AI

Known for efficient MoE architectures and groundbreaking reasoning models. DeepSeek-V3 and R1 series have achieved remarkable performance with innovative training techniques.

5

Models

4

Open Source

4

Categories

Visit Website →

Official Site

Models

DeepSeek-V3.2

671B (37B active) parameters

API
💬 Chat 🧠 Reasoning 💻 Coding

Latest V3 iteration with improved general capabilities. Enhanced reasoning and coding performance over V3.1.

  • SWE-bench Verified: 73.1%
  • Improved knowledge and academic tasks
  • LiveCodeBench-v6: 83.3%

Benchmarks

mmlu

88.5%

humaneval

90%

gsm8k

95.5%

Released Sep 1, 2025 131K context

DeepSeek-R1-0528

671B (37B active) parameters

Open Source API
🧠 Reasoning 🔢 Math 💻 Coding

Major reasoning upgrade. AIME 2025 accuracy improved from 70% to 87.5%. Performance approaching O3 and Gemini 2.5 Pro levels.

  • Intelligence Index: 68 (Artificial Analysis)
  • AIME 2025: 87.5%
  • Approaching frontier model performance

Benchmarks

mmlu

90.8%

humaneval

89.5%

gsm8k

97%

math

94.5%

Released May 28, 2025 131K context
HuggingFace

DeepSeek-V3-0324

671B (37B active) parameters

Open Source API
💬 Chat 🧠 Reasoning 💻 Coding

Significant benchmark improvements. MMLU-Pro: 75.9 to 81.2 (+5.3). GPQA: 59.1 to 68.4 (+9.3). AIME: 39.6 to 59.4 (+19.8).

  • MMLU-Pro: 81.2
  • GPQA: 68.4
  • LiveCodeBench: 49.2

Benchmarks

mmlu

87.5%

mmlu-pro

81.2%

gpqa

68.4%

humaneval

88%

Released Mar 24, 2025 131K context
HuggingFace

DeepSeek-V3

671B (37B active) parameters

Open Source API
💬 Chat 🧠 Reasoning 💻 Coding

Breakthrough MoE model. 671B parameters with only 37B activated per token. Innovative load balancing and multi-token prediction. Trained on 14.8T tokens.

  • Outperforms GPT-4o and Claude 3.5 Sonnet on MMLU
  • Cost-efficient MoE architecture
  • First fully open 600B+ model

Benchmarks

mmlu

87.1%

humaneval

86.5%

gsm8k

93%

Released Dec 26, 2024 131K context
HuggingFace

DeepSeek-Coder-V2

236B (21B active) parameters

Open Source API
💻 Coding

First open-source model to match GPT-4 Turbo on coding. Supports 338 programming languages. 128K context length.

  • HumanEval: 90.2%
  • MBPP: 76.2%
  • First open model >10% on SWE-bench

Benchmarks

humaneval

90.2%

mbpp

76.2%

Released Jun 17, 2024 128K context
HuggingFace