Sakana Fugu

Language Proprietary

Benchmarks

About Sakana Fugu

Sakana Fugu is an AI model developed by Sakana AI, in the language category, released in 2026, made available as a proprietary (API-only) model. A multi-agent orchestration model that behaves like a single LLM: one request to one OpenAI-compatible endpoint, and a l.

On this page you'll find Sakana Fugu's full specifications, including 3 benchmark results. Review provider pricing and benchmark scores below, or compare Sakana Fugu head-to-head with other language models.

→ More models by Sakana AI → All language models → AI benchmarks leaderboard

Community

Would you run Sakana Fugu again?

No votes yet — be the first.

Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Sakana Fugu benchmark scores▶

Compare on the benchmark table →

Benchmark	Category	Score
SWE-bench Pro	code	59%
GPQA Diamond	reasoning	95.5%
Humanity's Last Exam	reasoning	47.2%

More models like Sakana Fugu

Llama-3-70B-Synthia-v3.5

· 70B

Frequently asked questions

What is Sakana Fugu? ▶

A multi-agent orchestration model that behaves like a single LLM: one request to one OpenAI-compatible endpoint, and a l It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Sakana Fugu? ▶

Sakana Fugu was developed by Sakana AI and released in 2026.

Is Sakana Fugu open source or proprietary? ▶

Sakana Fugu is a proprietary model. It is accessed through an API rather than by downloading the weights.

How much does Sakana Fugu cost? ▶

Pricing for Sakana Fugu depends on the provider. See the providers table on this page for the latest API rates.

How does Sakana Fugu perform on benchmarks? ▶

Sakana Fugu is benchmarked across 3 evaluations on GenAIList, including SWE-bench Pro (59%). See the full benchmark table below and compare it with other models.