The Model Index
Models/OpenAI

o1

OpenAIClosed weightsReasoning

o1 is a closed AI model from OpenAI with an index score of 136 (GPT-4 = 100), rank 110 of 217.

136120–152Index score#110 of 217 modelsPro mode: 119
–Price per million tokensno public API price found
–Context windowtokens it reads at once
5 Dec 2024ReleasedReplaced by o3

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100o1

Among the first models to reach this score.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
77%
Humanity's Last Exam
8%
Mathsevidence
FrontierMath (tiers 1-3)
15%
Codingevidence
SWE-bench Verified
no result
Terminal-Bench 4.0
no result
Agentsevidence
APEX-Agents
no result
Professional workno evidence yet
Finance Agent (v2)
no result
Novel problemsno evidence yet
ARC-AGI-2
no result
Long tasksevidence
METR time horizon
31 sec

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

What others sayrank on each leaderboard

The Model Indexthird-party tests, our method#110of 217 · 136

Best attop three among current models

Replaced by o3; it no longer leads any category among current models.

Where to use itprices checked 18 Nov 2026

Host prices from OpenRouter; going direct can differ.

Facts and sources

Released5 Dec 2024
Announcementnot linked yet
Release entryo1 (full) + o1 pro
Scored aso1
Pro modeindex 119
Output speed–
Hugging Faceclosed weights

OpenAI releasesaround this one

This page as a chartDownload PNG