Up to four models
Llama 3.1-8B vs Llama 3.2 1B
On the index (GPT-4 = 100), Llama 3.1-8B scores 89 and Llama 3.2 1B 81. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
8970–107
WeightsOpen
ReleasedJul 2024
Price in / out$0.020 / $0.040
Context131K
Core tests taken1 of 9
8139–124
WeightsOpen
ReleasedSep 2024
Price in / out$0.027 / $0.20
Context60K
Core tests taken1 of 9
Llama 3.1-8B and Llama 3.2 1B are too close to call (7 points apart, within the uncertainty), ahead on 1 of 1 shared core tests, and costs 2.8× less.
Test by testthird-party results
Every result as a table
| Test | Llama 3.1-8B | Llama 3.2 1B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 27.0% | 23.9% |
| Maths | ||
| AIME-style maths (OTIS mock) | 1.7% | 0.6% |
| Agents | ||
| BALROG | 15.1% | 6.6% |
Tests at least two of these models have taken. Bold rows are the core tests.