Model dossier模型档案
Mistral Large
Mistral Large is an entry-tier model from Mistral AI (Intelligence Score 48.7/100). Strongest in knowledge (77) and math (64.4); best fit: knowledge QA and long-form writing. It trails in reasoning (26.6). Premium-priced: $2.00 in / $6.00 out per 1M tokens. Open weights — self-hostable.
Mistral Large 是 Mistral AI 的入门梯队模型(智能评分 48.7/100)。 最强项是知识(77分),其次是数学(64.4分);适合知识问答与长文写作。 短板是推理(26.6分)。 定价属高端定价:每百万 token 输入 $2.00 / 输出 $6.00。 开放权重,可自托管。
open weights开放权重
48.7
Intelligence Score · benchmark coverage 智能评分 · benchmark 覆盖 90%
◈
Benchmark scoresBenchmark 成绩
9 entries 条| Benchmark基准 | Score成绩 | Index指数 | Dated日期 | Measured by测评方 | |
|---|---|---|---|---|---|
| Humanity's Last ExamReasoning | 4.1 | 7 | — | 3rd-party第三方 | source ↗ |
| GPQA DiamondReasoning | 43.9 | 46 | 2026 | 3rd-party第三方 | source ↗×6⚠±24.1 |
| MMLU-ProKnowledge | 73.11 | 77 | — | 3rd-party第三方 | source ↗ |
| SWE-bench VerifiedCoding | 49.5 | 51 | 2026-08 | 3rd-party第三方 | source ↗×4 |
| AIME 2025Math | 85 | 85 | — | 3rd-party第三方 | source ↗×3⚠±71 |
| LiveCodeBenchCoding | 36.2 | 39 | — | 3rd-party第三方 | source ↗×2 |
| FrontierMathMath | 36.3 | 41 | — | 3rd-party第三方 | source ↗ |
| Terminal-BenchCoding | 66 | 72 | 2026-08-01 | 3rd-party第三方 | source ↗×2⚠±42.25 |
| LMArena (Chatbot Arena)Preference | 1415 | 29 | 2026-08-12 | official官方榜 | source ↗×3⚠±60 |
≡
Specs & pricing规格与价格
| Provider厂商 | Mistral AI |
|---|---|
| Released发布 | 2024-02-26 |
| Context window上下文 | 128K tokens |
| Max output最大输出 | 102K tokens |
| Modality模态 | text+file->text |
| Reasoning tiers推理档位 | not documented未见公开文档 |
| API input price输入价格 | $2.00 / 1M tokens |
| API output price输出价格 | $6.00 / 1M tokens |
⛓
Tools using this model使用它的工具
⚔
Head-to-head正面对比
How we score →评分方法 → · Catalog & pricing via the official OpenRouter API.模型目录与价格来自 OpenRouter 官方 API。