The Model Index
Up to four models

GPT-4o (Jan 2025) vs GPT-4o (Nov 2024)

On the index (GPT-4 = 100), GPT-4o (Jan 2025) scores 123 and GPT-4o (Nov 2024) 111. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to GPT-4o (Jan 2025)
Presets
GPT-4o (Jan 2025)
123107–139
WeightsClosed
ReleasedJan 2025
Price in / out–
Context–
Core tests taken0 of 9
GPT-4o (Nov 2024)
11194–127
WeightsClosed
ReleasedNov 2024
Price in / out$2.5 / $10
Context128K
Core tests taken3 of 9

GPT-4o (Jan 2025) leads GPT-4o (Nov 2024) by 13 points.

Test by testthird-party results

GPT-4o (Jan 2025)GPT-4o (Nov 2024)
0%25%50%75%100%CODINGAider PolyglotAider Polyglot
Every result as a table
TestGPT-4o (Jan 2025)GPT-4o (Nov 2024)
Coding
Aider Polyglot27.1%18.2%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG