The Model Index
Models/OpenAI

o3

OpenAIClosed weightsReasoning

o3 is a closed AI model from OpenAI with an index score of 147 (GPT-4 = 100), rank 75 of 217.

147131–163Index score#75 of 217 modelsPro mode: 145 · $20 / $80
$2.0/ $8.0Price per million tokensinput / output · via OpenRouter
200KContext windowtokens it reads at once
16 Apr 2025Released1 year 7 months ago

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100o3

Among the first models to reach this score.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
82%
Humanity's Last Exam
20%
Mathsevidence
FrontierMath (tiers 1-3)
33%
Codingevidence
SWE-bench Verified
62%
Terminal-Bench 4.0
no result
Agentsevidence
APEX-Agents
no result
Professional workevidence
Finance Agent (v2)
no result
Novel problemsevidence
ARC-AGI-2
7%
Long tasksevidence
METR time horizon
39 sec

Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.

What others sayrank on 10 leaderboards

Best attop three among current models

Where to use itprices checked 18 Nov 2026

API providers 1 · per 1M tokens, in / out

Host prices from OpenRouter; going direct can differ.

Facts and sources

Released16 Apr 2025
Announcementopenai.com ↗
Release entryo3 + o4-mini
Scored aso3
Pro modeindex 145 · $20 / $80 per M
Output speed–
Hugging Faceclosed weights

OpenAI releasesaround this one

This page as a chartDownload PNG