13 个模型 · 平均评分 77
在定价和模型深度的同时追踪可靠性，使服务商选择建立在运营现实之上。
All Systems Operational
Rolling availability across the last 30 days.
Composite reliability indicator from recent status behavior.
Includes degraded performance, partial outages, and major incidents.
| # | Model | Score |
|---|---|---|
| 6 | Claude Opus 4.6 | 92 |
| 9 | Claude Opus 4.5 | 90 |
| 12 | Claude Sonnet 4.6 | 89 |
| 13 | Claude Sonnet 4.5 | 89 |
| 54 | Claude Haiku 4.5 | 83 |
| 64 | Claude Opus 4.1 | 82 |
| 68 | Claude Opus 4 | 82 |
| 78 | Claude Sonnet 4 | 80 |
| 96 | Claude 3.7 Sonnet | 77 |
| 156 | Claude 3.7 Sonnet (thinking) | 70 |
| 179 | Claude 3.5 Sonnet | 66 |
| 207 | Claude 3.5 Haiku | 62 |
| 274 | Claude 3 Haiku | 43 |
| 排名 | 模型 | 评分 |
|---|---|---|
| #6 | Claude Opus 4.6 | 92 |
| #9 | Claude Opus 4.5 | 90 |
| #12 | Claude Sonnet 4.6 | 89 |
| #13 | Claude Sonnet 4.5 | 89 |
| #54 | Claude Haiku 4.5 | 83 |
| #64 | Claude Opus 4.1 | 82 |
| #68 | Claude Opus 4 | 82 |
| #78 | Claude Sonnet 4 | 80 |
| #96 | Claude 3.7 Sonnet | 77 |
| #156 | Claude 3.7 Sonnet (thinking) | 70 |
| #179 | Claude 3.5 Sonnet | 66 |
| #207 | Claude 3.5 Haiku | 62 |
| #274 | Claude 3 Haiku | 43 |
Anthropic目前在我们平台上提供13个AI模型，平均质量评分为77/100。
Anthropic评分最高的模型是Claude Opus 4.6，总排名第6名，综合评分92/100。
Anthropic模型的平均评分为77/100。他们最好的模型Claude Opus 4.6全球排名第6名。访问我们的服务商对比页面进行详细分析。