Up to four models
o3 vs Llama 4 Scout
On the index (GPT-4 = 100), o3 scores 147 and Llama 4 Scout 112. 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
o3 leads Llama 4 Scout by 35 points, ahead on 2 of 2 shared core tests, at 23× the price.
Test by testthird-party results
o3
Llama 4 Scout
Every result as a table
| Test | o3 | Llama 4 Scout |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 81.8% | 51.8% |
| Fiction.LiveBench | 88.9% | 36.0% |
| Maths | ||
| AIME-style maths (OTIS mock) | 84.4% | 7.8% |
| MATH (level 5) | 97.8% | 62.3% |
| FrontierMath (2025 set) | 18.7% | 0.0% |
| Agents | ||
| DTBench | 84.8% | 57.9% |
| LMCA | 39.7% | 12.0% |
| Novel problems | ||
| ARC-AGI-2 | 6.5% | 0.0% |
| ARC-AGI-1 | 75.7% | 0.5% |
Task length · METR39 sec
Tests at least two of these models have taken. Bold rows are the core tests.