SDF Chatter
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
ikt@aussie.zone to LocalLLaMA@sh.itjust.worksEnglish · 18 days ago

Kimi K3 is competitive with Fable; Kimi K3 + Fable is SoTA.

fireworks.ai

external-link
message-square
0
link
fedilink
  • cross-posted to:
  • hackernews@lemmy.bestiver.se
14
external-link

Kimi K3 is competitive with Fable; Kimi K3 + Fable is SoTA.

fireworks.ai

ikt@aussie.zone to LocalLLaMA@sh.itjust.worksEnglish · 18 days ago
message-square
0
link
fedilink
  • cross-posted to:
  • hackernews@lemmy.bestiver.se
Benchmarking over 1,000 agentic tasks demonstrates that routing between the open-source Kimi K3 model and the closed Fable 5 model creates a new state-of-the-art (SoTA) approach that surpasses the performance of either model alone. While both models perform competitively in general benchmarks, they possess distinct specializations—K3 excels in terminal, symbolic math, and dev tooling, whereas Fable leads in web, data visualization, and multi-language breadth. By architecting a router to leverage these specific strengths, teams can achieve a 93% task accuracy rate and up to 50x better cost-efficiency compared to using Fable in isolation, effectively proving that relying on a single model is no longer optimal.
alert-triangle
You must log in or register to comment.

LocalLLaMA@sh.itjust.works

localllama@sh.itjust.works

Subscribe from Remote Instance

Create a post
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !localllama@sh.itjust.works

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they’re still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 8 users / day
  • 192 users / week
  • 393 users / month
  • 867 users / 6 months
  • 48 local subscribers
  • 5K subscribers
  • 465 Posts
  • 2.4K Comments
  • Modlog
  • mods:
  • pax@sh.itjust.works
  • noneabove1182@sh.itjust.works
  • SmokeyDope@lemmy.world
  • MonsterBug@sh.itjust.works
  • BE: 0.19.20
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org