Up to four models
GPT-4o (Aug 2024) vs Llama 3.1
On the index (GPT-4 = 100), GPT-4o (Aug 2024) scores 112 and Llama 3.1 110. 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 (Aug 2024)
11295–128
WeightsClosed
ReleasedAug 2024
Price in / out$2.5 / $10
Context128K
Core tests taken2 of 9
GPT-4o (Aug 2024) and Llama 3.1 are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests.
Test by testthird-party results
GPT-4o (Aug 2024)
Llama 3.1
Every result as a table
| Test | GPT-4o (Aug 2024) | Llama 3.1 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 49.2% | 50.9% |
| MMLU (HELM runs) | 84.3% | 84.5% |
| SimpleBench | 17.8% | 23.0% |
| Maths | ||
| AIME-style maths (OTIS mock) | 6.4% | 9.7% |
| MATH (level 5) | 53.3% | 49.8% |
Tests at least two of these models have taken. Bold rows are the core tests.