DeepSeekDeepSeek R1Open SourceArena #42May 28, 2025

DeepSeek: R1 0528 (free)

May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.

Context Window
164K
tokens
Max Output
164K
tokens
Released
May 28, 2025
Arena Rank
#42
of 305 models
Output Speed
135
tokens/sec
Time to First Token
4.8s
TTFT

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
Prompt Caching
🖥Computer Use
🎨Image Generation

Supported Parameters

Frequency Penalty
Reduce repetition
Include Reasoning
Show reasoning tokens
Max Tokens
Output length limit
min_p
Presence Penalty
Encourage new topics
Reasoning
Extended thinking
Repetition Penalty
Penalize repeated tokens
Stop Sequences
Custom stop tokens
Temperature
Controls randomness
Top K
Top-K sampling
Top P
Nucleus sampling

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
OpenRouterFreeFree
Martian$0.40$1.75$0.20
DeepInfra$1.00$3.00

Benchmarks

Artificial Analysis
Intelligence IndexArtificial Analysis
70/100
Coding IndexArtificial Analysis
62/100
Math IndexArtificial Analysis
94/100
MMLU-PROArtificial Analysis
0.798/1
GPQA DiamondArtificial Analysis
0.718/1
MATH-500Artificial Analysis
0.972/1
AIME 2024Artificial Analysis
0.897/1
Humanity's Last ExamArtificial Analysis
0.088/1
LiveCodeBenchArtificial Analysis
0.655/1
SciCodeArtificial Analysis
0.408/1

Model IDs

OpenRouterdeepseek/deepseek-r1-0528:free

Tags

reasoning
Compare with another model

Related Models