Compare, 2 models
Side by side.
GPT-5.2 and Mistral Large 4 on every board at least two of them share. Blue marks the best in each row.
Specs
List prices, context and published output speed. Blue marks the best in each row.
| Spec | GPT-5.2OpenAI | Mistral Large 4Mistral |
|---|---|---|
| Lab | OpenAI | Mistral |
| Type | Language | Language |
| Released | Dec 11, 2025 | Oct 6, 2026 |
| Input price$ per 1M tokens | $1.75 | $1.36 |
| Output price$ per 1M tokens | $14.00 | $4.18 |
| Blended price3 input tokens per output | $4.81 | $2.07 |
| Contexttokens | 400K | 1.05M |
| Open weights | No | No |
Benchmarks
Every board where at least two of these models have a published score. Each score links to its source.
| Board | GPT-5.2OpenAI | Mistral Large 4Mistral |
|---|---|---|
| Epoch Capabilities IndexOverall, higher is better | 154 | 150 |
| LMArena textOverall, higher is better | 1437High, style control | 1433style control |
| FrontierMath Tiers 1-3Reasoning and knowledge, higher is better | 67.4%xhigh setting | 58.6%high setting |
| GPQA DiamondReasoning and knowledge, higher is better | 91.4%xhigh setting | 88.1%high setting |
n/a means the board has not published a score for that model.