Up to four models
GPT-3.5 Turbo (Jan 2024) vs Llama 3.1-8B
On the index (GPT-4 = 100), GPT-3.5 Turbo (Jan 2024) scores 90 and Llama 3.1-8B 89. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-3.5 Turbo (Jan 2024)
9072–109
WeightsClosed
ReleasedJan 2024
Price in / out–
Context–
Core tests taken2 of 9
8970–107
WeightsOpen
ReleasedJul 2024
Price in / out$0.020 / $0.040
Context131K
Core tests taken1 of 9
GPT-3.5 Turbo (Jan 2024) and Llama 3.1-8B are too close to call (2 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.
Test by testthird-party results
GPT-3.5 Turbo (Jan 2024)
Llama 3.1-8B
Every result as a table
| Test | GPT-3.5 Turbo (Jan 2024) | Llama 3.1-8B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 27.2% | 27.0% |
| MMLU (HELM runs) | 67.3% | 56.1% |
| Maths | ||
| AIME-style maths (OTIS mock) | 2.2% | 1.7% |
| MATH (level 5) | 11.6% | 22.9% |
| Coding | ||
| WeirdML | 3.5% | 1.7% |
| Agents | ||
| DTBench | 48.5% | 50.9% |
| LMCA | 9.7% | 5.4% |
Tests at least two of these models have taken. Bold rows are the core tests.