> o3 is a closed AI model from OpenAI, released 16 Apr 2025. Index score 147 (GPT-4 = 100), rank 63 of 229 ranked models. API price $2.0 in / $8.0 out per million tokens, 200K context.

[Models](https://themodelindex.org/models/) /[OpenAI](https://themodelindex.org/labs/openai/)

# o3

OpenAI

Released 16 Apr 2025

Closed

Reasoning

Date verified

[Compare](https://themodelindex.org/compare/o3-2025-04-vs-qwen3/) [Announcement](https://openai.com/index/introducing-o3-and-o4-mini/)

147136–158

Index score

#63 of 229 models

Pro mode: 148 · $20 / $80

6/ 8

Core tests taken

5 of 6 areas · plus 22 anchor tests

Frontier

Versus the frontier at release

set or matched the record

$2.0/ $8.0

Price per million tokens

input / output, list price

200K

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_

Among the first models to reach this score.

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

Show 16 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

82%

Humanity's Last Exam

20%

Maths

evidence

FrontierMath T1-3

33%

Coding

evidence

SWE-bench Verified

62%

Terminal-Bench

no result

Agents

evidence

APEX-Agents

no result

Novel problems

evidence

ARC-AGI-2

7%

Long tasks

evidence

METR time horizon

2.0 h

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

#63

of 219 · 147

Epoch Capabilities Index

overall capability from many benchmarks

#63

of 239 · 146.9

Artificial Analysis Intelligence Index

overall capability across ten evaluations

#56

of 207 · 20

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

3rd

SWE-bench Verified

Epoch AI · independent

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

ChatGPT

app · subscription

↗

OpenAI API

API

↗

#### API providers · 1 · per million tokens, in / out

O

OpenAI

$2.0 / $8.0

cheapest

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

16 Apr 2025

Announcement

[openai.com ↗](https://openai.com/index/introducing-o3-and-o4-mini/)

Release entry

o3 + o4-mini

Scored as

o3

Artificial Analysis index

20 (their estimate)

Pro mode

index 148 · $20 / $80 per M

Output speed

106 tokens/s

Hugging Face

closed weights

## OpenAI releases · around this one

GPT-4.5

Closed

27 FEB 2025

index 124

GPT-4.1

Closed

14 APR 2025

index 125

o3

Closed

16 APR 2025

index 147

o4-mini

Closed

16 APR 2025

index 143

codex-1

Closed

16 MAY 2025

---
Source: https://themodelindex.org/models/o3-2025-04/ · The Model Index · data as of 2026-10-01