GPT-4 with 128K context and knowledge through April 2023 — 3× cheaper than GPT-4
Latest iteration of GPT-4 with improved performance and longer context window
| Benchmark | GPT-4 Turbo | GPT-4 | Δ |
|---|---|---|---|
| MMLU | 86.4% | 86.4% | 0.0 |
| HumanEval | 67% | 67.0% | 0.0 |
| HellaSwag | 95.3% | — | — |