Up to four models
MiniMax-M3 vs o3
On the index (GPT-4 = 100), MiniMax-M3 scores 147 and o3 147. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
147131–164
WeightsOpen
ReleasedJun 2026
Price in / out$0.30 / $1.2
Context1.05M
Core tests taken4 of 9
MiniMax-M3 and o3 are too close to call (0 points apart, within the uncertainty), ahead on 1 of 1 shared core tests, and costs 6.7× less.
Test by testthird-party results
Every result as a table
| Test | MiniMax-M3 | o3 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 90.9% | 81.8% |
| GPQA Diamond (Vals AI) | 92.7% | 84.1% |
| MMLU Pro | 84.2% | 85.6% |
| MMMU Pro | 81.2% | 80.4% |
| SimpleBench | 45.8% | 53.1% |
| Maths | ||
| AIME-style maths (OTIS mock) | 71.1% | 84.4% |
| Chess puzzles | 17.0% | 37.0% |
| Coding | ||
| LiveCodeBench | 82.2% | 83.9% |
| Agents | ||
| DTBench | 78.9% | 84.8% |
| LMCA | 33.7% | 39.7% |
| Mystery game puzzles | 8.0% | 29.0% |
| Professional work | ||
| CorpFin v2 | 68.1% | 59.7% |
| LegalBench | 85.4% | 83.8% |
| MedCode | 46.3% | 47.3% |
| MedScribe | 87.3% | 76.6% |
| MortgageTax | 68.4% | 65.7% |
| TaxEval v2 | 72.7% | 74.6% |
Task length · METR39 sec
Tests at least two of these models have taken. Bold rows are the core tests.