
Real head-to-head · same prompt, one shot
Fugu Mini vs Qwen 3.7
Fugu's fast mini variant — single model, no panel, ~3 min per build. vs Multilingual open-weights — strong on Chinese reasoning.
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 Mini and Qwen 3.7, side by side, on 4 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 Mini · Dispatched from Agent OS as the fast Sakana lane. Bench scored by Claude judge against the same 42 prompts.
Qwen 3.7 · Wired alongside GLM-5.2 in Agent OS for open-weights agent loops where you want vendor diversity.
Side-by-side on 17 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 ↓
Fugu Mini
Qwen 3.7
Game
Page
Sim
Sim
Game
— not attempted —
Game
— not attempted —
Game
— not attempted —
Sim
— not attempted —
Sim
— not attempted —
Sim
— not attempted —
Sim
— not attempted —
Sim
— not attempted —
Sim
— not attempted —
Visual
— not attempted —
Visual
— not attempted —
Visual
— not attempted —
Visual
— not attempted —
Strengths & weaknesses I logged
Fugu Mini
Strengths
- Zero panel orchestration — much lower latency than Ultra
- Same Sakana subscription, no extra cost
- Doesn't time out on heavy game/3D prompts where Ultra stalls
Trade-offs
- Single model only — no ensemble verdict
- Newer than Ultra — less calibration / verification
Qwen 3.7
Strengths
- Open weights, free for individuals — same model class as GLM-5.2
- Best-of-three on fluid simulation in the Goldie Bench bench
- Multilingual depth — Chinese reasoning especially strong
Trade-offs
- Only 5 tasks scored on the bench so far — small sample size
- Trails GLM-5.2 on cinematic visual builds at similar pricing
Pricing & context — the spec sheet
| Spec | Fugu Mini | Qwen 3.7 |
|---|---|---|
| Vendor | Sakana AI | Alibaba |
| Context window | Single-model variant of Sakana's Fugu — no panel orchestration. Same API endpoint, much faster per call. | 256,000 tokens |
| Price | Same Sakana subscription pool as Fugu Ultra | Open weights · free for individuals |
| Pricing detail | The non-Ultra `fugu` model on Sakana's API. Sakana describes it as 'Fast mini model optimized for low latency yet high quality responses.' Crucially: zero orchestration tokens per call (vs Ultra's panel of thousands). Returns in ~3 min instead of 6-15 min and doesn't time out on heavy prompts. | Alibaba's open-weights release — downloadable from Hugging Face, runnable locally or via Alibaba Cloud's free tier for individuals. |
| Release | 2026-06-15 | 2026-06 |
| Bench coverage | 1/16 scored · avg 8.00/10 | 5/5 scored · avg 7.50/10 |
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 Mini and Qwen 3.7 both into the Agent Operating System and dispatch each from the kanban by task type — agent loops where latency matters more than panel consensus → Fugu Mini, open-weights alternative to glm-5.2 when you want a different model family → Qwen 3.7. That's the same setup I run for the 3,600+ founders inside the AI Profit Boardroom.
FAQ — Fugu Mini vs Qwen 3.7
Which is better, Fugu Mini or Qwen 3.7?
On Goldie Bench, Fugu Mini averages no scored verdicts yet across the shared tasks, with 0 gold, 0 silver, 0 bronze overall. Qwen 3.7 averages no scored verdicts yet, with 0 gold, 0 silver, 1 bronze. Not enough scored shared tasks yet to call a winner.
How much does Fugu Mini cost vs Qwen 3.7?
Fugu Mini: The non-Ultra `fugu` model on Sakana's API. Sakana describes it as 'Fast mini model optimized for low latency yet high quality responses.' Crucially: zero orchestration tokens per call (vs Ultra's panel of thousands). Returns in ~3 min instead of 6-15 min and doesn't time out on heavy prompts. Qwen 3.7: Alibaba's open-weights release — downloadable from Hugging Face, runnable locally or via Alibaba Cloud's free tier for individuals.
What's the context window for Fugu Mini vs Qwen 3.7?
Fugu Mini has a Single-model variant of Sakana's Fugu — no panel orchestration. Same API endpoint, much faster per call. context window. Qwen 3.7 has a 256,000 tokens context window.
When should I pick Fugu Mini over Qwen 3.7?
Pick Fugu Mini for: Agent loops where latency matters more than panel consensus; Quick first-drafts you'll refine downstream; Filling out a bench when Ultra is timing out. The trade-off is the weaknesses we logged on the bench: Single model only — no ensemble verdict; Newer than Ultra — less calibration / verification.
When should I pick Qwen 3.7 over Fugu Mini?
Pick Qwen 3.7 for: Open-weights alternative to GLM-5.2 when you want a different model family; Multilingual workloads (Chinese, multi-script content); Fluid and particle simulations. The trade-off is the weaknesses we logged on the bench: Only 5 tasks scored on the bench so far — small sample size; Trails GLM-5.2 on cinematic visual builds at similar pricing.
How does Goldie Bench score Fugu Mini vs Qwen 3.7?
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 Mini vs Fugu Ultra Qwen 3.7 vs Fugu Ultra Fugu Mini vs Fusion Qwen 3.7 vs Fusion Fugu Mini vs Opus 4.8 Qwen 3.7 vs Opus 4.8 Fugu Mini vs GLM-5.2 Qwen 3.7 vs GLM-5.2Full model pages: Fugu Mini · Qwen 3.7 · back to the leaderboard
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
$100k+/mocommunity MRR

















