Up to four models
GPT-4 Turbo vs DeepSeek LLM 67B
On the index (GPT-4 = 100), GPT-4 Turbo scores 107 and DeepSeek LLM 67B 87. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-4 Turbo leads DeepSeek LLM 67B by 20 points, ahead on 1 of 1 shared core tests.
Test by testthird-party results
GPT-4 Turbo
DeepSeek LLM 67B
Every result as a table
| Test | GPT-4 Turbo | DeepSeek LLM 67B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 42.4% | 24.6% |
| Maths | ||
| MATH (level 5) | 40.0% | 6.4% |
Task length · METR21 sec
Tests at least two of these models have taken. Bold rows are the core tests.