Model dossier模型档案
Claude Sonnet 5
Claude Sonnet 5 is a high-tier model from Anthropic (Intelligence Score 83.6/100). Strongest in knowledge (92.2) and reasoning (89.1); best fit: knowledge QA and long-form writing. It trails in preference (40.8). Premium-priced: $2.00 in / $10 out per 1M tokens. Context window 1M tokens — long-document friendly.
Claude Sonnet 5 是 Anthropic 的高水平梯队模型(智能评分 83.6/100)。 最强项是知识(92.2分),其次是推理(89.1分);适合知识问答与长文写作。 短板是偏好(40.8分)。 定价属高端定价:每百万 token 输入 $2.00 / 输出 $10。 上下文 1M token,长文档友好。
83.6
Intelligence Score · benchmark coverage 智能评分 · benchmark 覆盖 100%
◈
Benchmark scoresBenchmark 成绩
11 entries 条| Benchmark基准 | Score成绩 | Index指数 | Dated日期 | Measured by测评方 | |
|---|---|---|---|---|---|
| Humanity's Last ExamReasoning | 57.4 | 100 | 2026-08 | 3rd-party第三方 | source ↗×4⚠±14.2 |
| GPQA DiamondReasoning | 74.6 | 78 | — | 3rd-party第三方 | source ↗×6⚠±21.6 |
| MMLU-ProKnowledge | 87.55 | 92 | — | 3rd-party第三方 | source ↗×3 |
| SWE-bench VerifiedCoding | 85.2 | 89 | 2026-08 | 3rd-party第三方 | source ↗×7⚠±12.5 |
| AIME 2025Math | 57.4 | 57 | — | 3rd-party第三方 | source ↗×3⚠±39.6 |
| LiveCodeBenchCoding | 82.43 | 88 | — | 3rd-party第三方 | source ↗×3⚠±19.23 |
| FrontierMathMath | 87 | 98 | — | 3rd-party第三方 | source ↗×2⚠±85.4 |
| Terminal-BenchCoding | 80.4 | 87 | — | official官方榜 | source ↗×6 |
| τ²-benchAgent | 80.4 | 81 | — | 3rd-party第三方 | source ↗ |
| LMArena (Chatbot Arena)Preference | 1462⚡high | 41 | 2026-08-12 | official官方榜 | source ↗×6 |
| WebArenaAgent | 64.5 | 70 | — | 3rd-party第三方 | source ↗×2 |
≡
Specs & pricing规格与价格
| Provider厂商 | Anthropic |
|---|---|
| Released发布 | 2026-06-30 |
| Context window上下文 | 1M tokens |
| Max output最大输出 | 128K tokens |
| Modality模态 | text+image+file->text |
| Reasoning tiers推理档位 | ⚡low ⚡medium ⚡high default默认 high · low / medium / high |
| API input price输入价格 | $2.00 / 1M tokens |
| API output price输出价格 | $10 / 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。