The Model Index
Up to four models

DeepSeek-R1 vs GPT-4o (Jan 2025)

On the index (GPT-4 = 100), DeepSeek-R1 scores 130 and GPT-4o (Jan 2025) 123. 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 DeepSeek-R1
Presets
DeepSeek-R1
130114–146
WeightsOpen
ReleasedJan 2025
Price in / out–
Context–
Core tests taken2 of 9
GPT-4o (Jan 2025)
123107–139
WeightsClosed
ReleasedJan 2025
Price in / out–
Context–
Core tests taken0 of 9

DeepSeek-R1 leads GPT-4o (Jan 2025) by 7 points.

Test by testthird-party results

DeepSeek-R1GPT-4o (Jan 2025)
0%25%50%75%100%REASONING & KNOWLEDGEFiction.LiveBenchFiction.LiveBenchCODINGAider PolyglotAider Polyglot
Every result as a table
TestDeepSeek-R1GPT-4o (Jan 2025)
Reasoning & knowledge
Fiction.LiveBench69.4%66.7%
Coding
Aider Polyglot56.9%27.1%
Task length · METR31 sec

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

This page as a chartDownload PNG