Sakana Fugu Technical Report — AI model

Yujin Tang, Edoardo Cetin, Jinglue Xu, Qi Sun, Stefan Nielsen, Vincent Richard, Haruto Goda, Iaroslav Tymchenko, Nhan Nguyen, Hyunin Lee, Mari Ashiga, Shashank Kotyan, So Kuroki, Tarin Clanuwat/Sakana Fugu Technical ReportUnknown

The capabilities of frontier Large Language Models (LLMs) continue to advance, with different providers increasingly specializing in distinct domains. This raises a natural next objective: how to combine the individual specializations of various LLMs into a collectively intelligent system. To this end, we report the development of Sakana Fugu, a family of orchestrator models that harness and amplify the capabilities of an LLM agent team. Fugu models are themselves language models trained to understand user queries and dynamically devise agentic scaffolds to solve them. Through these adaptive scaffolds, Fugu accesses performance beyond any individual LLM agent, achieving state-of-the-art results compared to other publicly accessible models across a range of challenging tasks, including SWE-Bench Pro, Terminal Bench, LiveCodeBench, GPQA-Diamond, Humanity's Last Exam, and CharXiv Reasoning. We release two models: Fugu, which balances performance with latency for everyday use, and Fugu-Ultra, which prioritizes answer quality on the hardest problems. We describe our training paradigm, which encompasses large-scale fine-tuning, evolutionary algorithms, and reinforcement learning approaches, along with the infrastructure and core design principles that turn these methods into a production system. We hope this report encourages further research into multi-agent systems and dynamic, query-adaptive agentic scaffolds as a path toward the next frontier of AI capabilities, accessed through collective intelligence.

model

Stars0

Forks0

HF Downloads—30d

Last commit—

Refreshed3mo ago

Project healthUnknownNo activity data.

Production readinessResearch / EarlyBest for exploration and prototyping.

Risk notesUnknown licenseVerify license before production use.

AgentHub Score

55 / 100

Composite score from 6 signals. How we score →

Active project

55Score

Growth

40C

Activity

30C

Documentation

70C+

Maturity

45C

Community

42C

Production

58C

GitHub stars · 80 days observed0 not enough history

snapshots

Repository activity · 80 days observedReal snapshots from pushed_at

inactivepushed

2026-07-262026-10-15

Practical assessment

Should you use it?

✓ Best for

Tool use and function calling
Agent reasoning tasks
Structured output generation

◎ Strengths

Open weights
Local deployment possible
Active model development

✕ Not ideal for

Production without proper evaluation
Tasks requiring 100% reliability

⚠ Watch-outs

Benchmark scores may not reflect production performance
Check licensing restrictions

Technical details

What's inside

Language—

License—

Sourcearxiv

Open source✗ No

Commercial use—

Docs—

Demo—

PaperarXiv ↗

AgentHub Score

Score 55/100

Below average

Alternatives

ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping

0 · model

RALI@iKAT 2026: Retrieval-aware User Profile Denoising via Personalized Conversational Dense Retrieval

0 · model

ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping

0 · model

Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety

0 · model

55 Compare all →

Recent activity

Latest commit ——

Indexed by AgentHub crawler3mo ago

Monitor for new releasesongoing