AITOPAI热报
ModelsMulti-source

Kimi K3 vs Fable 智能体任务评测：路由策略以93%准确率降低50倍成本

Fireworks AI@FireworksAI_HQ
Post· 11 sources
View the post
Why we picked it

Fireworks 用1000个智能体任务实测了 Kimi K3 和 Fable，发现按任务路由能省50倍成本，还能保持93%准确率。K3 在安全和长循环上更强。

Fireworks AI 在约1000个智能体任务上对比了 Kimi K3 和 Fable。K3 在安全、加密和长终端循环任务上领先，Fable 在多语言和网页/数据可视化上占优。

Body

通过每任务路由，准确率达93%，在长循环上成本比 Fable 低50倍。路由器将72-96%流量导向K3。

K3 将于7月27日在 Fireworks 上线。

Original · Fireworks AI

We ran Kimi K3 against Fable on ~1,000 agentic tasks, expecting a catch-up story. We got a specialization story instead. @kimi_moonshot 's K3 outperformed on security, crypto, and long terminal loops. Fable beat on multi-lang + web/data viz. Per-task routing hits 93% accuracy, above BOTH models, at up to 50x lower cost than Fable on long loops. The part nobody's pricing in yet: the router sends 72-96% of traffic to K3. The frontier model becomes the fallback rather than the default. Kimi K3, coming to Fireworks July 27.📊 2 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Kimi K3, Fable, Fireworks AI, agents.

Source attribution: curated from Fireworks AI (@FireworksAI_HQ). Cross-source corroboration: 11 independent sources have covered this development (including lmarena.ai, SuperTechFans, IT之家), confirming industry-wide signal strength.

#Kimi K3#Fable#Fireworks AI#agents#routing strategies

Keep reading

Recent stories with the same tag or section
PapersBuildersMulti-source00:53
Chinese contentGoogle DeepMind 论文：多智能体攻击可突破 Gemini 4 Argon 的提示注入防御

DeepMind 用 8 组攻击智能体互相学习迭代，结果 Gemini 4 Argon 也被攻破 34% 的任务，开源模型更是几乎全败。做智能体工具调用的开发者都得看看，别以为人测不出漏洞就安全了。

#Gemini 4 Argon#Google DeepMind#Kimi K3#prompt engineering
Event
rohanpaul_ai@rohanpaul_aiSource
How-toBuildersMulti-source15:35
Chinese content网友用停产傲腾内存无显卡跑通 Kimi K3，每秒输出 1.5 词元

这个折腾太硬核了：一块显卡都没有，靠停产的傲腾内存加至强 CPU 跑通月之暗面那个 2.8 万亿参数的 Kimi K3，用 llama.cpp 推理，1 比特量化最快每秒 1.5 个词元。速度感人但证明了家用硬件也能啃超大模型，对喜欢搞本地部署的玩家很有参考价值。

#Kimi K3#llama.cpp#Intel Optane#Moonshot AI
Event
IT之家Source
PapersBuildersMulti-source10:59
Chinese contentEvoX 论文提出把 Agent Harness 视作运行时策略

一篇关于 agent 工程的硬核论文：EvoX 用 Rust 写的运行时层去管住模型落地时的工具调用、中断恢复和结果校验，不靠记忆和插件就拿到 691 组测试里 56.2% 的成功率。做 agent 框架或工程化落地的开发者建议看看它对 GLM-5.3 和 Kimi K3 提升最大的原因。

#EvoX#agent#papers#GLM-5.3
Event
arXiv cs.AI@Haoyang Zhang et al. (6)Source
PapersUS vs ChinaOfficial10:35
Chinese content姚期智与杨植麟联合发布 TCSExam 基准，Kimi K3 刷新图论纪录

姚期智和杨植麟一起做了个理论计算机科学基准，用 Lean 4 自动判分，Kimi K3 还顺手刷了个 124 顶点 630 边的图论纪录。做形式化验证或模型评测的人可以看看它的出题思路。

#TCSExam#Kimi K3#Lean 4#reasoning models
Event
Primary sourcepandaily@[email protected] (Pandaily)Source
PapersBuildersMulti-sourceSelected10:28
Together Compiler Hits 2.6x Speedups on Frontier Model Inference

An agent loop that continuously recompiles inference engines against live traffic could shift how serving providers keep pace with rapidly changing model architectures, replacing static hand-tuned kernels. Teams running inference infrastructure or building MoE serving stacks can study the tiered persistent engine design and context-management ablations for their own optimizer setups. The results also benchmark directly against open source engines on Chinese frontier models like DeepSeek v4.1 Flash and Kimi K3, a useful comparison point when evaluating serving providers.

#Together AI#inference optimization#compilers#DeepSeek v4.1 Flash
Event
arXiv: DeepSeek@Reyna Abhyankar et al. (12)Source
ProductsUS vs ChinaMulti-sourceSelected01:12
Together Compiler Hits 2.7× Throughput Gain on B200 and B300

The gap between 1.5× and 2.7× across models suggests the compiler's optimizations are architecture-dependent, so teams should benchmark their specific model before committing. Teams self-hosting or choosing an inference provider for Kimi, GLM, DeepSeek, or MiniMax models can use these figures to compare serving costs. Together's pitch targets the growing ecosystem serving Chinese open-weight models on NVIDIA's B-series hardware.

#Together AI#Kimi K3#DeepSeek#inference optimization
Event
Official accountTogether AI@togethercomputeSource