Mistral Large 2411
开源来自 Mistral AI · 发布于 2024-11-19
45.8
平均分
$2.00/1M
输入价格
$6.00/1M
输出价格
131K tokens (~66 books)
上下文窗口
text
类型
Tested on 11 benchmarks with 45.8% average. Top scores: Chatbot Arena Elo — Overall (1304.7%), HELM — IFEval (87.6%), HELM — WildBench (80.1%).
基准测试分数
| 基准测试 | 类别 | 分数 | Bar |
|---|---|---|---|
| Chatbot Arena Elo — Overall | arena | 1304.7 | |
| HELM — IFEval | language | 87.6 | |
| HELM — WildBench | reasoning | 80.1 | |
| Aider — Code Editing | coding | 65.4 | |
| HELM — MMLU-Pro | knowledge | 59.9 | |
| MATH level 5 | math | 50.3 | |
| HELM — GPQA | knowledge | 43.5 | |
| GPQA diamond | knowledge | 35.1 | |
| HELM — Omni-MATH | math | 28.1 | |
| OTIS Mock AIME 2024-2025 | math | 7.7 | |
| FrontierMath-2025-02-28-Private | math | 0.3 |