> DeepSeek-R1 is an open-weights AI model from DeepSeek, released 20 Jan 2025. Index score 129 (GPT-4 = 100), rank 120 of 229 ranked models.

[Models](https://themodelindex.org/models/) /[DeepSeek](https://themodelindex.org/labs/deepseek/)

# DeepSeek-R1

DeepSeek

Released 20 Jan 2025

Open

Reasoning

[Compare](https://themodelindex.org/compare/deepseek-r1-vs-o1/) [Announcement](https://api-docs.deepseek.com/news/news250120/)

129118–141

Index score

#120 of 229 models

3/ 8

Core tests taken

3 of 6 areas · plus 9 anchor tests

−6

Versus the frontier at release

best then: o1

Replaced by [DeepSeek-R1-0528](https://themodelindex.org/models/deepseek-r1-0528/)

–

Price per million tokens

no public API price found

–

Context window

tokens it reads at once

## Where it sits · on the frontier

_Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_

o1 reached this score 2 months earlier.

## Test results · by area · tick = best by any model

Show 7 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

69%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

no result

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

no result

Novel problems

evidence

ARC-AGI-2

1%

Long tasks

evidence

METR time horizon

27 min

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

## What others say · rank on each leaderboard

The Model Index

independent tests, our method

#120

of 219 · 129

LMArena · Maths

maths questions in chat

#121

of 373 · 1412

LMArena · Creative writing

creative writing

#130

of 386 · 1374

LMArena · Text

overall chat quality, judged by people

#143

of 388 · 1398

LMArena · Coding

coding questions in chat

#142

of 383 · 1444

Epoch Capabilities Index

overall capability from many benchmarks

#100

of 239 · 141.3

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

## Best at · top three among current models

Replaced by DeepSeek-R1-0528; it no longer leads any category among current models.

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

## Where to use it · prices checked 1 Oct 2026

#### From the lab

DeepSeek Chat

app · subscription

↗

DeepSeek API

API

↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

## Facts and sources

Released

20 Jan 2025

Announcement

[api-docs.deepseek.com ↗](https://api-docs.deepseek.com/news/news250120/)

Release entry

DeepSeek-R1

Scored as

DeepSeek-R1

Artificial Analysis index

–

Output speed

–

Hugging Face

not linked

## DeepSeek releases · around this one

DeepSeek-R1-Lite-Preview

Closed

20 NOV 2024

DeepSeek-V3

Open

26 DEC 2024

index 116

DeepSeek-R1

Open

20 JAN 2025

index 129

DeepSeek-R1-0528

Open

28 MAY 2025

index 134

DeepSeek-V3.1

Open

21 AUG 2025

index 132

---
Source: https://themodelindex.org/models/deepseek-r1/ · The Model Index · data as of 2026-10-01