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.
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
Every result as a table
| Test | DeepSeek-R1 | GPT-4o (Jan 2025) |
|---|---|---|
| Reasoning & knowledge | ||
| Fiction.LiveBench | 69.4% | 66.7% |
| Coding | ||
| Aider Polyglot | 56.9% | 27.1% |
Task length · METR
31 sec
Tests at least two of these models have taken. Bold rows are the core tests.