The Model Index
Models/OpenAI

GPT-5 nano

OpenAIClosed weights

GPT-5 nano is a closed AI model from OpenAI with an index score of 125 (GPT-4 = 100), rank 146 of 217.

125109–141Index score#146 of 217 models
$0.050/ $0.40Price per million tokensinput / output · via OpenRouter
400KContext windowtokens it reads at once
7 Aug 2025ReleasedReplaced by GPT-5.4 Nano

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100GPT-5 nano

o1 reached this score 8 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
69%
Humanity's Last Exam
no result
Mathsevidence
FrontierMath (tiers 1-3)
20%
Codingevidence
SWE-bench Verified
no result
Terminal-Bench 4.0
no result
Agentsevidence
APEX-Agents
no result
Professional workevidence
Finance Agent (v2)
no result
Novel problemsevidence
ARC-AGI-2
3%
Long tasksno evidence yet
METR time horizon
no result

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

What others sayrank on 9 leaderboards

Best attop three among current models

Replaced by GPT-5.4 Nano; 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

Released7 Aug 2025
Announcementnot linked yet
Release entry–
Scored asGPT-5 nano
Output speed–
Hugging Faceclosed weights

OpenAI releasesaround this one

This page as a chartDownload PNG