Kilo

Kilo Code

Fable 5-class intelligence at ~59% less. The split-the-cost play.

ContextVaries — Kilo splits planning from execution across multiple models

Pricing~59% less than Fable 5 solo

Tasks tested0

Avg scorecurrently unranked

Medals🥇0 🥈0 🥉0

Release2026-06-16

Official sitekilocode.ai ↗

Official vendor source

Kilo Code is built by Kilo — see the vendor's own product page, pricing, and docs at kilocode.ai.

Visit kilocode.ai →

Reference benchmarks for Kilo Code

These are external benchmarks I pulled from the source comparison guides on agentos.guide — SWE-bench Verified, DRACO, Kilo plan rubric, build-time measurements, vendor-reported coding scores. They are not goldiebench medal scores (those come only from same-prompt one-shot creative coding tasks in the matrix). I surface them here so the spec sheet for Kilo Code is honest about what's measured.

Cheaper-plan quality (GPT-5.5 cohort)

8.3/10

source: /kilo-split

Cost reduction vs solo Fable 5

~59% less

source: /kilo-split

What is Kilo Code?

Kilo Code is the Kilo frontier model with a Varies — Kilo splits planning from execution across multiple models context window, released 2026-06-16. Tagline: Fable 5-class intelligence at ~59% less. The split-the-cost play.. Official source: kilocode.ai.

Pricing detail. Kilo Code is a routing layer that splits planning (heavy model) from execution (cheaper model) so you get Fable-5-class plans driving GPT-5.5-class builds. Total spend lands at ~59% less than running Fable 5 end-to-end.

How I use it inside the Agent OS. Used inside Agent OS as a routing layer: Fable 5 generates the plan, cheaper models execute. Bench scoring pending a head-to-head comparison.

What I built with Kilo Code

Every model on Goldie Bench gets the same fixed prompt set — one shot, single HTML file out — and I score the result 0–10 inside the Agent Operating System. Here's what Kilo Code shipped on the bench: 0 one-shot demos across Varies — Kilo splits planning from execution across multiple models of context. Of those, 0 are scored against the field with my honest 0–10 from the source guides at agentos.guide.

Strengths

Kilo's own rubric: Fable 5 plan = 9.1/10, GPT-5.5 plan = 8.3/10 — Kilo isolates where the intelligence actually lives
Plan quality stays high while execution cost drops
Drop-in for Agent OS — Kilo Split framework already wired

Trade-offs

Adds routing complexity — two model providers in one workflow
No per-task goldiebench head-to-heads yet

Best for

Cost-conscious operators who run high-volume agent loops
Multi-step workflows where the plan is the expensive part
Teams already paying for Fable 5 who want to keep the plan but drop the execution bill

Every demo by Kilo Code

0 live demos, sorted by category. Click any tile to play the actual one-shot result. Verdicts and 0–10 scores are pulled from the source guides where I posted them publicly.

every demo, in a grid · click any one to play

Compare Kilo Code against every other model

Every head-to-head featuring Kilo Code. Verdicts shown for scored pairs.