Up to four models
o3 vs Llama 4 Maverick
On the index (GPT-4 = 100), o3 scores 147 and Llama 4 Maverick 116. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
116100–132
WeightsOpen
ReleasedApr 2025
Price in / out$0.35 / $1.0
Context524K
Core tests taken3 of 9
o3 leads Llama 4 Maverick by 31 points, ahead on 3 of 3 shared core tests, at 6.8× the price.
Test by testthird-party results
o3
Llama 4 Maverick
Every result as a table
| Test | o3 | Llama 4 Maverick |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 81.8% | 67.0% |
| Humanity's Last Exam | 20.3% | 5.7% |
| GPQA Diamond (Vals AI) | 84.1% | 69.4% |
| MMLU Pro | 85.6% | 79.4% |
| MMMU Pro | 80.4% | 71.7% |
| Fiction.LiveBench | 88.9% | 46.2% |
| GeoBench | 74.0% | 52.0% |
| SimpleBench | 53.1% | 27.7% |
| Maths | ||
| AIME-style maths (OTIS mock) | 84.4% | 20.6% |
| MATH (level 5) | 97.8% | 73.0% |
| MATH 500 | 94.6% | 85.2% |
| MGSM | 91.8% | 92.4% |
| FrontierMath (2025 set) | 18.7% | 0.7% |
| Coding | ||
| Aider Polyglot | 81.3% | 15.6% |
| LiveCodeBench | 83.9% | 47.3% |
| WeirdML | 52.4% | 24.5% |
| Agents | ||
| DTBench | 84.8% | 61.9% |
| LMCA | 39.7% | 15.9% |
| Professional work | ||
| CorpFin v2 | 59.7% | 49.7% |
| LegalBench | 83.8% | 77.8% |
| MedCode | 47.3% | 36.5% |
| MedScribe | 76.6% | 54.2% |
| MortgageTax | 65.7% | 58.5% |
| TaxEval v2 | 74.6% | 66.6% |
| Novel problems | ||
| ARC-AGI-2 | 6.5% | 0.0% |
| ARC-AGI-1 | 75.7% | 4.4% |
Task length · METR39 sec
Tests at least two of these models have taken. Bold rows are the core tests.