Real head-to-head · same prompt, one shot

Hy3 vs Kilo Code

Tencent's open-weights coder — Apache-2.0, cheap, beats GLM-5.1 on frontend in Tencent's blind eval. vs Fable 5-class intelligence at ~59% less. The split-the-cost play.

Hy3 · context262K tokens
Kilo Code · contextVaries (Kilo dispatches across models)
Hy3 · price$0.14 / 1M input · $0.58 / 1M output
Kilo Code · price~59% less than Fable 5 solo
Hy3 · vendorTencent Hunyuan
Kilo Code · vendorKilo

What I tested — same prompt, two models

I run the same fixed prompt set through every new model the day it drops — same string, one shot, single HTML file out — and I score the result 0–10 on whether it ran, how close it hit the brief, and how good it looked. Below is what came out when I gave the exact same prompts to Hy3 and Kilo Code, side by side, on 0 shared tasks inside the Agent Operating System.

Both models were given identical prompts inside the Agent Operating System — no help, no iteration, no "best of N" tricks. I run each prompt once, save the HTML file the model produces, and score it 0–10 on whether it ran, how close it hit the brief, and how good it looked. The scoring is mine. The verdicts below are pulled from my source comparison guides at agentos.guide where I publish every score and the reasoning behind it.

Hy3 · Wired into the Agent OS as the 'Hy3 Coder' tab (chat + live preview + workspace) via OpenRouter. Bench built one-shot on the same prompts as the field; weak builds iterated by Hy3 itself (the model fixes its own builds).

Kilo Code · Used inside Agent OS as a routing layer: Fable 5 generates the plan, cheaper models execute. Bench scoring pending a head-to-head comparison.

Side-by-side on 7 shared tasks

Click any cell to play that model's actual one-shot attempt. Medals are derived from my 0–10 scores per task (highest = 🥇, second = 🥈, third = 🥉).

Task ↓
Hy3
Kilo Code
Game
Hy3 on Doom
— not attempted —
Hy3 on Dragonrealm
— not attempted —
Game
🥈Hy3 on Flightsim
— not attempted —
Game
Hy3 on Gtadrive
— not attempted —
Game
Hy3 on Gtafoot
— not attempted —
Game
Hy3 on Parachute
— not attempted —
Page
Hy3 on Aipbpromo
— not attempted —

Strengths & weaknesses I logged

Hy3

Strengths

  • Apache-2.0 open weights — self-host free, no lock-in
  • Tencent's 270-expert blind eval: 2.67/4 vs GLM-5.1's 2.51, strongest on frontend / data / CI-CD
  • Hallucination rate cut 12.5% → 5.4%; stable tool-calls across scaffoldings (<4% SWE-Bench variance)

Trade-offs

  • Slow upstream on OpenRouter (30-90s per build) — fine for one-shots, sluggish for tight loops
  • One-shot game builds can under-render (flat raycaster walls, unlit 3D) without an iterate pass

Kilo Code

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

Pricing & context — the spec sheet

Spec Hy3 Kilo Code
VendorTencent HunyuanKilo
Context window262,144-token context window. Open weights (Apache-2.0) on HuggingFace / ModelScope / GitHub; benched here via OpenRouter.Varies — Kilo splits planning from execution across multiple models
Price$0.14 / 1M input · $0.58 / 1M output~59% less than Fable 5 solo
Pricing detailTencent Hunyuan 3 — open-weights under Apache-2.0, so free to self-host. On OpenRouter it is one of the cheapest capable coders: ~$0.14/M in, $0.58/M out (1 RMB / 4 RMB). Upstream can be slow (30-90s to first token), but per-token cost is negligible.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.
Release2026-07-062026-06-16
Bench coverage7/7 scored · avg 7.13/100/0 scored · avg —

The verdict — which should you pick?

Not enough scored shared tasks yet for a head-to-head average. The live demos for both are on the matrix above — play them and form your own opinion.

If you only run one of these inside your stack, the head-to-head average above is the call. If you can run both, my honest play is to wire Hy3 and Kilo Code both into the Agent Operating System and dispatch each from the kanban by task type — cost-sensitive coding + frontend design where open weights matter → Hy3, cost-conscious operators who run high-volume agent loops → Kilo Code. That's the same setup I run for the 3,600+ founders inside the AI Profit Boardroom.

FAQ — Hy3 vs Kilo Code

Which is better, Hy3 or Kilo Code?

On Goldie Bench, Hy3 averages no scored verdicts yet across the shared tasks, with 0 gold, 1 silver, 0 bronze overall. Kilo Code averages no scored verdicts yet, with 0 gold, 0 silver, 0 bronze. Not enough scored shared tasks yet to call a winner.

How much does Hy3 cost vs Kilo Code?

Hy3: Tencent Hunyuan 3 — open-weights under Apache-2.0, so free to self-host. On OpenRouter it is one of the cheapest capable coders: ~$0.14/M in, $0.58/M out (1 RMB / 4 RMB). Upstream can be slow (30-90s to first token), but per-token cost is negligible. Kilo Code: 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.

What's the context window for Hy3 vs Kilo Code?

Hy3 has a 262,144-token context window. Open weights (Apache-2.0) on HuggingFace / ModelScope / GitHub; benched here via OpenRouter. context window. Kilo Code has a Varies — Kilo splits planning from execution across multiple models context window.

When should I pick Hy3 over Kilo Code?

Pick Hy3 for: Cost-sensitive coding + frontend design where open weights matter; Self-hosters who want an Apache-2.0 model they fully own; Anyone wiring a cheap capable coder into a live build panel (Agent OS Hy3 Coder tab). The trade-off is the weaknesses we logged on the bench: Slow upstream on OpenRouter (30-90s per build) — fine for one-shots, sluggish for tight loops; One-shot game builds can under-render (flat raycaster walls, unlit 3D) without an iterate pass.

When should I pick Kilo Code over Hy3?

Pick Kilo Code 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. The trade-off is the weaknesses we logged on the bench: Adds routing complexity — two model providers in one workflow; No per-task goldiebench head-to-heads yet.

How does Goldie Bench score Hy3 vs Kilo Code?

Every demo on this page was built by Julian Goldie inside the Agent Operating System — same fixed prompt for both models, one shot, single HTML file out. Each result gets a 0–10 score on whether it ran, how close it hit the brief, and how good it looked. The highest score on each task gets gold; second gets silver; third gets bronze. See methodology for full provenance.

The same stack Julian uses

Run this stack yourself.

Every demo on this bench was built inside the Agent Operating System — one prompt, one shot, single HTML file out. The Agent OS, the prompts, the templates, the weekly walkthroughs and 3,600+ founders shipping with it every day all live inside the AI Profit Boardroom.

3,600+founders
258documented wins
38countries
$59/momonthly