Up to four models
GPT-5.2 vs Mistral Large 3
On the index (GPT-4 = 100), GPT-5.2 scores 162 and Mistral Large 3 117. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-5.2
162146–178
WeightsClosed
ReleasedDec 2025
Price in / out$1.75 / $14
Context400K
Core tests taken6 of 9
11799–135
WeightsOpen
ReleasedDec 2025
Price in / out$0.50 / $1.5
Context262K
Core tests taken0 of 9
GPT-5.2 leads Mistral Large 3 by 45 points, at 6.4× the price.
Test by testthird-party results
GPT-5.2
Mistral Large 3
Every result as a table
| Test | GPT-5.2 | Mistral Large 3 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Vals AI) | 91.7% | 68.4% |
| MMLU Pro | 86.2% | 79.8% |
| MMMU Pro | 86.7% | 66.2% |
| SimpleBench | 45.8% | 20.4% |
| Maths | ||
| MGSM | 94.0% | 85.4% |
| Coding | ||
| LiveCodeBench | 85.4% | 55.3% |
| SWE-bench | 75.8% | 41.4% |
| Agents | ||
| DTBench | 90.9% | 65.1% |
| LMCA | 43.9% | 16.7% |
| Professional work | ||
| CorpFin v2 | 65.9% | 61.0% |
| LegalBench | 82.8% | 79.1% |
| MortgageTax | 67.1% | 52.1% |
| TaxEval v2 | 75.8% | 73.1% |
Task length · METR45 sec
Tests at least two of these models have taken. Bold rows are the core tests.