Compare, 2 models
Side by side.
GPT-6 Luna 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-6 LunaOpenAI | Mistral Large 4Mistral |
|---|---|---|
| Lab | OpenAI | Mistral |
| Type | Language | Language |
| Released | Sep 22, 2026 | Oct 29, 2026 |
| Input price$ per 1M tokens | $0.10 | $0.70 |
| Output price$ per 1M tokens | $0.50 | $2.10 |
| Blended price3 input tokens per output | $0.20 | $1.05 |
| Contexttokens | 1.05M | 1.05M |
| Open weights | No | Yes |
| Output speedTok / s | 126 | n/a |
Benchmarks
Every board where at least two of these models have a published score. Each score links to its source.
| Board | GPT-6 LunaOpenAI | Mistral Large 4Mistral |
|---|---|---|
| Artificial Analysis Intelligence IndexOverall, higher is better | 28Max | 26High |
| Epoch Capabilities IndexOverall, higher is better | 157 | 155 |
| LMArena textOverall, higher is better | 1441Max, style control | 1432style control |
| GPQA DiamondReasoning and knowledge, higher is better | 90.5%max setting | 90.2%high setting |
n/a means the board has not published a score for that model.