Up to four models
GPT-4 (Jun 2023) vs Llama 2-13B
On the index (GPT-4 = 100), GPT-4 (Jun 2023) scores 102 and Llama 2-13B 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 (Jun 2023)
10285–119
WeightsClosed
ReleasedJun 2023
Price in / out$30 / $60
Context8K
Core tests taken1 of 9
GPT-4 (Jun 2023) leads Llama 2-13B by 15 points.
Test by testthird-party results
GPT-4 (Jun 2023)
Llama 2-13B
Every result as a table
| Test | GPT-4 (Jun 2023) | Llama 2-13B |
|---|---|---|
| Reasoning & knowledge | ||
| MMLU (HELM runs) | 82.4% | 55.4% |
| Agents | ||
| DTBench | 62.7% | 42.2% |
Tests at least two of these models have taken. Bold rows are the core tests.