Fusion vs Fugu Ultra

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 Fusion and Fugu Ultra, side by side, on 42 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.

Fusion · Dispatched from Agent OS for research-heavy prompts where ensemble accuracy outweighs single-model speed.

Fugu Ultra · Dispatched from Agent OS as the panel-ensemble alternative to OpenRouter Fusion. Bench scored by Claude judge against the same 42 prompts as every other model.

Where Fusion beat Fugu Ultra

The tasks where I gave Fusion a higher 0–10 score on the same prompt — with the actual commentary from my source guides.

Where Fugu Ultra beat Fusion

The tasks where I gave Fugu Ultra a higher 0–10 score on the same prompt — with the actual commentary from my source guides.

Strengths & weaknesses I logged

Pricing & context — the spec sheet

The verdict — which should you pick?

Across 42 scored shared tasks, Fusion averaged 8.60/10, beating Fugu Ultra's 7.94/10 by 0.65 points. Pick Fusion when the build has to ship on the first prompt and you can afford the trade-offs in the comparison below.

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 Fusion and Fugu Ultra both into the Agent Operating System and dispatch each from the kanban by task type — deep-research workflows where panel consensus beats single-model answers → Fusion, teams that want fusion-class quality but need a different vendor risk profile → Fugu Ultra. That's the same setup I run for the 4,000+ founders inside the AI Profit Boardroom.

FAQ — Fusion vs Fugu Ultra

Which is better, Fusion or Fugu Ultra?

On Goldie Bench, Fusion averages 8.60/10 across the shared tasks, with 21 gold, 3 silver, 3 bronze overall. Fugu Ultra averages 7.94/10, with 5 gold, 2 silver, 2 bronze. Fusion wins the head-to-head 26–4.

How much does Fusion cost vs Fugu Ultra?

Fusion: OpenRouter's Fusion API dispatches a single prompt to multiple frontier models and ensembles the answers. Premium panel: Fable 5 + GPT-5.5. Budget panel: cheaper open-weights models. Roughly half the per-token cost of a Fable 5 solo call. Fugu Ultra: Sakana's multi-agent orchestration: a single API call internally dispatches to multiple frontier models and synthesises the answer. Subscription plans run $20-$200/mo (Standard / Pro / Max); PAYG is $5/M input + $30/M output for Fugu Ultra. Direct competitor to OpenRouter Fusion's panel approach.

What's the context window for Fusion vs Fugu Ultra?

Fusion has a Varies — depends on which panel models are dispatched context window. Fugu Ultra has a 272,000 tokens with the standard rate. Calls exceeding 272K context are billed at the higher 'long-context' rates. context window.

When should I pick Fusion over Fugu Ultra?

Pick Fusion for: Deep-research workflows where panel consensus beats single-model answers; Cost-sensitive operators who want Fable-5-class output at ~half the bill; Production agents that benefit from vendor-redundancy on every call. The trade-off is the weaknesses we logged on the bench: Ensemble latency higher than any single model (panel calls run in parallel but the slowest still gates the response); No per-task goldiebench scoring yet — bench rank pending.

When should I pick Fugu Ultra over Fusion?

Pick Fugu Ultra for: Teams that want Fusion-class quality but need a different vendor risk profile; Operators avoiding export-controlled providers (Sakana emphasises this in their pitch); Deep-research workflows where ensemble verdicts beat single-model answers. The trade-off is the weaknesses we logged on the bench: Panel orchestration adds latency — even a 'pong' burns ~2k orchestration tokens; Newer than Fusion; less community calibration on long-tail prompts.

How does Goldie Bench score Fusion vs Fugu Ultra?

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:

Full model pages: Fusion · Fugu Ultra · back to the leaderboard