R1 0528
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.
Input
Output
Context
131K
Max Output
33K
Parameters
671B
Technical Specifications
Model TypeChat
Context Window131K
Max Output Tokens33K
Parameters671B
Training Cutoff—
Licensemit
Capabilities
Input Modalities
text
Output Modalities
text
Features
code_generationreasoning
Benchmarks
Chatbot Arena
#8
Rank (Text)
+5/-5
arena text ci 95
1427
Arena Score (Text)
18,284
Votes (Text)
Artificial Analysis
14.9%
HLE
89.3%
AIME
81.3%
GPQA
40.3%
SciCode
98.3%
MATH 500
84.9%
MMLU Pro
76.0
Math
24.0
Coding
77.0%
LiveCodeBench
27.1
Intelligence
Resources & Links
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.