Anthropic 发布的 Claude Fable 5.2 (xHigh) 在 Arena 的 Code Arena: WebDev 榜单以 1832 分排名第一，超过 Claude Opus 5.5 (Max) 的 1818 分和 Gemini 4 Carbon (High) 的 1768 分。据 Arena 数据，该模型比 Fable 5.1 快最多 30%，价格从每百万 tokens $10/$50 降至 $8/$40，Agent Arena 分数即将公布。
Big news: Claude Fable 5.2 (xHigh) by @AnthropicAI has landed #1 in the Code Arena: WebDev with 1832 pts. This update is up to 30% faster than Fable 5.1, and more cost efficient: $8/$40 per M tokens, down from $10/$50.
This real-world performance puts it ahead of:
- Claude Opus 5.5 (Max) at 1818
- Gemini 4 Carbon (High) at 1768
- GPT-6 Astra (Max) at 1767
Congrats to the @AnthropicAI team on this release! 👏
Stay tuned for Agent Arena scores.
在 X 查看被引用的帖子Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
来源：Arena.ai · x.com
事件后续 · 5
查看事件全部- 同事件Claude Fable 5.2 上线 Higgsfield，开放 3 天免费试用Higgsfield AI · 5 小时前
- 同事件Artificial Analysis 评测 Claude Fable 5.2：以 65 分登顶 Intelligence Index v5Artificial Analysis · 5 小时前
- 同事件Claude Fable 5.2 上线 Devin Desktop 和 Devin CLICognition · 5 小时前
- 同事件Anthropic 用 1000 个 Claude Fable 5.2 智能体在沙箱内复现费马大定理形式化证明Anthropic：Claude.dev 开发者博客 · 5 小时前
- 同事件Anthropic 发布 Claude Fable 5.2 与 Claude Mythos 5.2Anthropic：Newsroom · 6 小时前