Up to four models
Mistral Large 3 vs Llama 4 Maverick
On the index (GPT-4 = 100), Mistral Large 3 scores 117 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.
11799–135
WeightsOpen
ReleasedDec 2025
Price in / out$0.50 / $1.5
Context262K
Core tests taken0 of 9
116100–132
WeightsOpen
ReleasedApr 2025
Price in / out$0.35 / $1.0
Context524K
Core tests taken3 of 9
Mistral Large 3 and Llama 4 Maverick are too close to call (1 point apart, within the uncertainty), at 1.5× the price.
Test by testthird-party results
Every result as a table
| Test | Mistral Large 3 | Llama 4 Maverick |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Vals AI) | 68.4% | 69.4% |
| MMLU Pro | 79.8% | 79.4% |
| MMMU Pro | 66.2% | 71.7% |
| SimpleBench | 20.4% | 27.7% |
| Maths | ||
| MGSM | 85.4% | 92.4% |
| Coding | ||
| LiveCodeBench | 55.3% | 47.3% |
| Agents | ||
| DTBench | 65.1% | 61.9% |
| LMCA | 16.7% | 15.9% |
| Professional work | ||
| CorpFin v2 | 61.0% | 49.7% |
| LegalBench | 79.1% | 77.8% |
| MortgageTax | 52.1% | 58.5% |
| TaxEval v2 | 73.1% | 66.6% |
Tests at least two of these models have taken. Bold rows are the core tests.