Fugu Ultra 1.1 vs Kilo Code
Sakana's multi-agent orchestrator, v1.1 — routes experts per request. vs Fable 5-class intelligence at ~59% less. The split-the-cost play.
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 Fugu Ultra 1.1 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.
Fugu Ultra 1.1 · Benched on GoldieBench via Sakana's Responses API (fugu-ultra-v1.1, xhigh reasoning). Game tasks use the skill-infused threejs-game-director prompt plus a controls+graphics fix loop with an anti-regression clamp, judged on a real mid-play frame by the same Opus judge as the field.
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 0 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 = 🥉).
Strengths & weaknesses I logged
Fugu Ultra 1.1
Strengths
- Orchestrates 1-3 expert agents per request and synthesises their answers
- Reported SWE-Bench Pro 73.7 — above Opus 4.8 and GPT-5.5 on Sakana's table
- OpenAI- and Anthropic-compatible API — drop-in for Codex and Claude Code
Trade-offs
- Benched as a partial run until the full 50-task batch completes
- Region-locked: unavailable across the EU/EEA/UK/CH — access depends on where you are
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 | Fugu Ultra 1.1 | Kilo Code |
|---|---|---|
| Vendor | Sakana AI | Kilo |
| Context window | 1,000,000-token context window | Varies — Kilo splits planning from execution across multiple models |
| Price | API · orchestration billed | ~59% less than Fable 5 solo |
| Pricing detail | Sakana's Fugu Ultra v1.1 — a multi-agent system served as a model: an orchestrator routes each request across one to three expert agents and synthesises the answer. Reported (v1.0): SWE-Bench Pro 73.7, LiveCodeBench 93.2, GPQA Diamond 95.5. NOTE: Sakana geo-blocks the EU/EEA/UK/Switzerland pending GDPR compliance — benched from an allowed region. | 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. |
| Release | 2026-07 | 2026-06-16 |
| Bench coverage | 0/0 scored · avg — | 0/0 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 Fugu Ultra 1.1 and Kilo Code both into the Agent Operating System and dispatch each from the kanban by task type — hard, high-stakes coding and reasoning where answer quality beats latency → Fugu Ultra 1.1, cost-conscious operators who run high-volume agent loops → Kilo Code. That's the same setup I run for the 4,000+ founders inside the AI Profit Boardroom.
FAQ — Fugu Ultra 1.1 vs Kilo Code
Which is better, Fugu Ultra 1.1 or Kilo Code?
On Goldie Bench, Fugu Ultra 1.1 averages no scored verdicts yet across the shared tasks, with 0 gold, 0 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 Fugu Ultra 1.1 cost vs Kilo Code?
Fugu Ultra 1.1: Sakana's Fugu Ultra v1.1 — a multi-agent system served as a model: an orchestrator routes each request across one to three expert agents and synthesises the answer. Reported (v1.0): SWE-Bench Pro 73.7, LiveCodeBench 93.2, GPQA Diamond 95.5. NOTE: Sakana geo-blocks the EU/EEA/UK/Switzerland pending GDPR compliance — benched from an allowed region. 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 Fugu Ultra 1.1 vs Kilo Code?
Fugu Ultra 1.1 has a 1,000,000-token context window context window. Kilo Code has a Varies — Kilo splits planning from execution across multiple models context window.
When should I pick Fugu Ultra 1.1 over Kilo Code?
Pick Fugu Ultra 1.1 for: Hard, high-stakes coding and reasoning where answer quality beats latency; Agentic workflows in Codex / Claude Code via the drop-in provider config; One-shot builds you want a panel of experts on, not a single model. The trade-off is the weaknesses we logged on the bench: Benched as a partial run until the full 50-task batch completes; Region-locked: unavailable across the EU/EEA/UK/CH — access depends on where you are.
When should I pick Kilo Code over Fugu Ultra 1.1?
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 Fugu Ultra 1.1 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.
Related comparisons
Other head-to-heads using the same scoring system:
Fugu Ultra 1.1 vs Fusion Kilo Code vs Fusion Fugu Ultra 1.1 vs Hermes MoA Kilo Code vs Hermes MoA Fugu Ultra 1.1 vs GPT-5.6 Sol Kilo Code vs GPT-5.6 Sol Fugu Ultra 1.1 vs Claude Fable 5 Kilo Code vs Claude Fable 5Full model pages: Fugu Ultra 1.1 · Kilo Code · back to the leaderboard
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 4,000+ founders shipping with it every day all live inside the AI Profit Boardroom.