Up to four models
Llama 4 Scout vs Llama 3.1
On the index (GPT-4 = 100), Llama 4 Scout 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.
11296–128
WeightsOpen
ReleasedApr 2025
Price in / out$0.10 / $0.30
Context1.31M
Core tests taken2 of 9
Llama 4 Scout and Llama 3.1 are too close to call (2 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.
Test by testthird-party results
Every result as a table
| Test | Llama 4 Scout | Llama 3.1 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 51.8% | 50.9% |
| Maths | ||
| AIME-style maths (OTIS mock) | 7.8% | 9.7% |
| MATH (level 5) | 62.3% | 49.8% |
| Agents | ||
| DTBench | 57.9% | 61.4% |
Tests at least two of these models have taken. Bold rows are the core tests.