Up to four models
GPT-4 Turbo vs Llama 3.2
On the index (GPT-4 = 100), GPT-4 Turbo scores 107 and Llama 3.2 106. 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 and Llama 3.2 are too close to call (1 point apart, within the uncertainty), ahead on 1 of 1 shared core tests.
Test by testthird-party results
GPT-4 Turbo
Llama 3.2
Every result as a table
| Test | GPT-4 Turbo | Llama 3.2 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 42.4% | 41.0% |
| MMLU (HELM runs) | 79.6% | 80.3% |
| Maths | ||
| MATH (level 5) | 40.0% | 39.4% |
Task length · METR21 sec
Tests at least two of these models have taken. Bold rows are the core tests.