Claude Fable 5.2 (Max) 登顶 Agent Arena，净改进领先第二名 30.4%
Anthropic 这版把 Agent Arena 的分数直接拉开了一倍多差距，Code 和 Work 也都冲到第一，API 还降价 20%。做智能体和编程工作流的朋友可以试试，尤其在意可控性的场景；预算紧的话 GPT-6.1 Terra 每任务不到 1 美元，性价比更合适。
Anthropic 的 Claude Fable 5.2 (Max) 在 Agent Arena 上排名第一，净改进 +30.4%，约是第二名 Claude Opus 5.5（+19.5%）的 1.6 倍，评测基于全球社区约 4.7k 次真实智能体会话。它在 Code、Chat、Work 三个分类也全部第一，同时在 Pareto 前沿上以 $7.3/任务的中位成本领先，比第三名 Gemini 4 Carbon (High)（+17.0%/$1.5/任务）性能更高但价格也明显更贵。
相比上一代 Claude Fable 5.1 (Max)，Fable 5.2 的排名从 #5 升至 #1，净改进从 +14.8% 提升到 +30.4%，中位成本从 $7.7/任务降到 $7.3/任务（低 6%），API 定价从 $10/$50 降至 $8/$40 每百万输入/输出 token（低 20%）。分项信号上，它在四项指标全部优于 5.1：Praise vs. Complaint +73%（第二名模型仅 +41%）、Steerability +33%、Confirmed Success +22%、Bash Reliability +14%。
与竞品对比，Fable 5.2 的净改进约为 GPT-6.1-Sol (Max)（+12.5%）的 2.4 倍，但每任务成本 $7.3 也高于 GPT-6.1 Terra (Max) 的 $0.9。对开发者而言，Code 分类从 5.1 的 #6 跃升到 #1（+19.8%）、Work 从 #4 到 #1（+15.8%），说明这代在真实编程和工作流任务的提升最集中。
Claude Fable 5.2 (Max) is now #1 on Agent Arena, leading the Pareto frontier in real-world agentic performance! Top models on Pareto Frontiers: - #1 Claude Fable 5.2 (Max): +30.4% | $7.3/task - #2 Claude Opus 5.5 (Max): +19.5% | $5.5/task - #3 Gemini 4 Carbon (High): +17.0% | $1.5/task - #7 GPT-6.1-Sol (Max): +12.5% | $1.1/task - #8 GPT-6.1 Terra (Max): +10.8% | $0.9/task Fable 5.2 delivers over 1.5x the net improvement of the #2 model, Opus 5.5, at a 32% higher median cost per task. Compared to Fable 5.1, it also delivers roughly 2x the net improvement at a 6% lower cost. Congrats again to the @AnthropicAI team on this impressive release! Arena.ai @arena Big news: Claude Fable 5.2 (Max) by @AnthropicAI takes #1 in Agent Arena with an unprecedented lead: +30.4% net improvement, about 1.6x the #2 model Opus-5.5, across 4.7k real-world agentic sessions from our global community. It's also #1 in Code, Chat and Work. A major leap over Claude Fable 5.1 (Max) - Rank: #5 → #1 , Net improvement: +14.8% → +30.4% - Median cost per task: $7.7 → $7.3 (6% lower). The API pricing $10/$50 → $8/$40 per million input/output tokens (20% lower) vs. The Frontiers - #1 Claude Fable 5.1 (Max): +30.4% | $7.3/task - #2 Claude Opus 5.5 (Max):+19.5%) | $5.5/task - #3 Gemini 4 Carbon (High):+17.0%) | $1.5/task - #6 GPT-6-Astra (Max): +14.5% | $6.0/task Breaking down performance across signals: Fable 5.2 improves over 5.1 across all four reported signals, with particularly large gains in user satisfaction and steerability. - #1 Praise vs. Complaint , +73%, biggest jump vs +41% the next model. - #1 Steerability: +33% - #1 Confirmed Success: +22% - #3 Bash Reliability: +14% #1 across all major categories - #1 Code: +34% - #1 Work: +31% - #1 Chat: +27% - Versus Fable 5.1: Code #6 → #1 (+19.8 %), Work #4 → #1 (+15.8 %), Chat #6 → #1 (+12.0%). Huge congrats to the @AnthropicAI team on this incredible release! 🔗 View Quoted Tweet📊 9 ⚡
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Claude, AnthropicAI, Agent Arena, GPT-6.1.
Source attribution: curated from lmarena.ai (@lmarena_ai). Cross-source corroboration: 11 independent sources have covered this development (including 宝玉, berryxia, IT之家), confirming industry-wide signal strength.
