
Qwen 3.7 vs Fugu Mini
Multilingual open-weights — strong on Chinese reasoning. vs Fugu's fast mini variant — single model, no panel, ~3 min per build.
Head-to-head verdict: Qwen 3.7 wins 1–0.
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 Qwen 3.7 and Fugu Mini, side by side, on 5 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.
Qwen 3.7 · Wired alongside GLM-5.2 in Agent OS for open-weights agent loops where you want vendor diversity.
Fugu Mini · Dispatched from Agent OS as the fast Sakana lane. Bench scored by Claude judge against the same 42 prompts.
Side-by-side on 27 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 = 🥉).
Where Qwen 3.7 beat Fugu Mini
The tasks where I gave Qwen 3.7 a higher 0–10 score on the same prompt — with the actual commentary from my source guides.
What I saw: GLM built the densest, most colourful city (windowed skyscrapers + speed/coins HUD). Opus ran the furthest with the cleanest motion. Qwen's is atmospheric — a foggy tunnel of buildings — but more muted and it crashes quicker.
Strengths & weaknesses I logged
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
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
Pricing & context — the spec sheet
| Spec | Qwen 3.7 | Fugu Mini |
|---|---|---|
| Vendor | Alibaba | Sakana AI |
| Context window | 256,000 tokens | Single-model variant of Sakana's Fugu — no panel orchestration. Same API endpoint, much faster per call. |
| Price | Open weights · free for individuals | Same Sakana subscription pool as Fugu Ultra |
| Pricing detail | Alibaba's open-weights release — downloadable from Hugging Face, runnable locally or via Alibaba Cloud's free tier for individuals. | 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. |
| Release | 2026-06 | 2026-06-15 |
| Bench coverage | 5/5 scored · avg 7.50/10 | 2/27 scored · avg 5.50/10 |
The verdict — which should you pick?
Across 1 scored shared tasks, Qwen 3.7 averaged 7.00/10, beating Fugu Mini's 3.00/10 by 4.00 points. Pick Qwen 3.7 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 Qwen 3.7 and Fugu Mini both into the Agent Operating System and dispatch each from the kanban by task type — open-weights alternative to glm-5.2 when you want a different model family → Qwen 3.7, agent loops where latency matters more than panel consensus → Fugu Mini. That's the same setup I run for the 3,600+ founders inside the AI Profit Boardroom.
FAQ — Qwen 3.7 vs Fugu Mini
Which is better, Qwen 3.7 or Fugu Mini?
On Goldie Bench, Qwen 3.7 averages 7.00/10 across the shared tasks, with 0 gold, 0 silver, 1 bronze overall. Fugu Mini averages 3.00/10, with 0 gold, 0 silver, 0 bronze. Qwen 3.7 wins the head-to-head 1–0.
How much does Qwen 3.7 cost vs Fugu Mini?
Qwen 3.7: Alibaba's open-weights release — downloadable from Hugging Face, runnable locally or via Alibaba Cloud's free tier for individuals. 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.
What's the context window for Qwen 3.7 vs Fugu Mini?
Qwen 3.7 has a 256,000 tokens context window. Fugu Mini has a Single-model variant of Sakana's Fugu — no panel orchestration. Same API endpoint, much faster per call. context window.
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.
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.
How does Goldie Bench score Qwen 3.7 vs Fugu Mini?
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:
Qwen 3.7 vs Fusion Fugu Mini vs Fusion Qwen 3.7 vs Opus 4.8 Fugu Mini vs Opus 4.8 Qwen 3.7 vs GLM-5.2 Fugu Mini vs GLM-5.2 Qwen 3.7 vs Grok Fugu Mini vs GrokFull model pages: Qwen 3.7 · Fugu Mini · 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 3,600+ founders shipping with it every day all live inside the AI Profit Boardroom.

























