> DeepSeek-V3 (Mar 2025) is an open-weights AI model from DeepSeek, released 24 Mar 2025. Index score 123 (GPT-4 = 100), rank 133 of 229 ranked models. API price $0.29 in / $1.14 out per million tokens, 164K context.

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

# DeepSeek-V3 (Mar 2025)

DeepSeek

Released 24 Mar 2025

Open

[Compare](https://themodelindex.org/compare/deepseek-v3-mar-2025-vs-o3-2025-04/)

123112–134

Index score

#133 of 229 models

2/ 8

Core tests taken

2 of 6 areas · plus 9 anchor tests

−13

Versus the frontier at release

best then: o1

Replaced by [DeepSeek-V3.1](https://themodelindex.org/models/deepseek-v3-1/)

$0.29/ $1.14

Price per million tokens

input / output, list price

164K

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 4 months earlier.

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

Show 7 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

68%

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

no evidence yet

ARC-AGI-2

no result

Long tasks

evidence

METR time horizon

23 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

#133

of 219 · 123

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-V3.1; 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

↗

#### API providers · 2 · per million tokens, in / out

S

StreamLake

$0.26 / $1.03

cheapest

D

DeepInfra

$0.32 / $0.89 · fp4

↗

#### Run it yourself

🤗

Official weights

deepseek-ai/DeepSeek-V3

↗

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

24 Mar 2025

Announcement

not linked yet

Release entry

–

Scored as

DeepSeek-V3 (Mar 2025)

Artificial Analysis index

–

Output speed

–

Hugging Face

[deepseek-ai/DeepSeek-V3-0324 ↗](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324)

## DeepSeek releases · around this one

DeepSeek Coder

Open

2 NOV 2023

DeepSeek LLM 67B

Open

29 NOV 2023

index 82

---
Source: https://themodelindex.org/models/deepseek-v3-mar-2025/ · The Model Index · data as of 2026-10-01