Up to four models
o3-mini vs Grok-3 mini
On the index (GPT-4 = 100), o3-mini scores 131 and Grok-3 mini 131. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
o3-mini and Grok-3 mini are too close to call (1 point apart, within the uncertainty), ahead on 2 of 2 shared core tests.
Test by testthird-party results
o3-miniGrok-3 mini
Every result as a table
| Test | o3-mini | Grok-3 mini |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 77.0% | 76.3% |
| GPQA Diamond (Vals AI) | 75.5% | 79.3% |
| MMLU Pro | 78.7% | 81.4% |
| Fiction.LiveBench | 50.0% | 66.7% |
| Maths | ||
| AIME-style maths (OTIS mock) | 76.9% | 77.8% |
| MATH (level 5) | 96.5% | 90.9% |
| MATH 500 | 91.8% | 94.2% |
| MGSM | 91.3% | 90.4% |
| FrontierMath (2025 set) | 12.4% | 5.9% |
| Coding | ||
| Aider Polyglot | 60.4% | 49.3% |
| LiveCodeBench | 71.5% | 76.2% |
| WeirdML | 43.8% | 42.6% |
| Professional work | ||
| CorpFin v2 | 45.3% | 61.1% |
| LegalBench | 71.5% | 83.1% |
| TaxEval v2 | 69.4% | 73.0% |
| Novel problems | ||
| ARC-AGI-2 | 3.0% | 0.4% |
| ARC-AGI-1 | 34.5% | 16.5% |
Tests at least two of these models have taken. Bold rows are the core tests.