The AI arena is free today

Open Superagent
DeepSeekReleased on Jan 20, 2025

DeepSeek R1 Zero: Benchmarks, Pricing & Context Window

DeepSeek R1 Zero is a language model from DeepSeek, released in January 2025.

DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with

DeepSeek R1 Zero benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for DeepSeek R1 Zero across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How DeepSeek R1 Zero holds up as conversations get longer.

Quality Tracker

DeepSeek R1 Zero Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Fri Oct 09 2026
Notice missing or incorrect data?

DeepSeek R1 Zero model size

DeepSeek R1 Zero has 671 billion parameters and was trained on 14.8 trillion tokens. See how it compares to other models in the same parameter range.

ParametersTraining tokens
671B
14.8Ttokens
22× tokens-to-params ratio
Frontier (200B+)
671B
1B7B70B405B

Try now

huggle
DeepSeek R1 Zeroin Huggle

Make it with
DeepSeek R1 Zero.

DeepSeek R1 Zero

DeepSeek R1 Zero latency

DeepSeek R1 Zero time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

DeepSeek R1 Zero examples

Recent arena outputs from DeepSeek R1 Zero, picked from the highest-ranked matchups.

DeepSeek R1 Zero license

DeepSeek R1 Zero is released under the MIT license, which permits commercial use, has 671.0B parameters.

License
MIT
Commercial use allowed
Parameters
671.0B

MIT License - allows commercial use

DeepSeek R1 Zero resources

Official sources for DeepSeek R1 Zero: provider documentation, official playground, paper or system card, source repository, model weights.

DeepSeek R1 Zero vs other models

The most-compared alternatives to DeepSeek R1 Zero are o1-pro, Kimi-k1.5, DeepSeek R1 Distill Llama 70B. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like DeepSeek R1 Zero

Models ranked just above and below DeepSeek R1 Zero by LLM Stats score.

 

o1-pro

Score pending
 

Kimi-k1.5

Score pending
 

DeepSeek R1 Distill Llama 70B

Score pending
 

LongCat-Flash-Chat

Score pending
 

DeepSeek-V3 0324

Score pending
 

Phi 4 Mini Reasoning

Score pending

FAQ

Common questions about DeepSeek R1 Zero.

When was DeepSeek R1 Zero released?

DeepSeek R1 Zero was released on January 20, 2025 by DeepSeek. This is the official DeepSeek R1 Zero release date tracked on LLM Stats.

How big is DeepSeek R1 Zero?

DeepSeek R1 Zero has 671 billion parameters. It was trained on 14.8 trillion tokens. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created DeepSeek R1 Zero?

DeepSeek R1 Zero was created by DeepSeek.

What is the license for DeepSeek R1 Zero?

DeepSeek R1 Zero is released under the MIT license. This is an open-source / open-weight license that permits self-hosting.

Where is the DeepSeek R1 Zero paper or technical report?

DeepSeek R1 Zero has a paper or technical report available at https://arxiv.org/abs/2501.12948. Use that source for architecture, training, release and evaluation details.

What models should I compare DeepSeek R1 Zero against?

Common DeepSeek R1 Zero comparisons include DeepSeek R1 Zero vs o1-pro, DeepSeek R1 Zero vs Kimi-k1.5, DeepSeek R1 Zero vs DeepSeek R1 Distill Llama 70B. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.