Preferred on Google

Sakana Fugu-Ultra v1.1 boosts AI performance

Sakana AI's Fugu-Ultra v1.1 orchestration engine sees performance gains and adds a Claude Code-compatible interface.

Editor, StartupHub.ai

Jul 24 at 10:02 AMUpdated Aug 22, 20261 min read

Sakana AI introduces Fugu-Ultra v1.1 with enhanced AI orchestration capabilities.· Sakana

Visual TL;DR

Sakana AICore

company pushing AI performance with new orchestration engine

From the article 4 mentionsSakana AI is pushing the envelope with its latest orchestration engine, announcing Fugu-Ultra v1.1.

Fugu-Ultra v1.1Core

new orchestration engine with significant performance improvements over previous version

From the article 4 mentionsThis upgrade reportedly allows Fugu-Ultra to outperform leading models like Fable 5 in complex coding and reasoning tasks, even without direct access to Fable within its agent pool.

Performance GainsEffect

up to 7.9 points gain, outperforming Fable 5 in complex tasks

From the article 2 mentionsThe company claims significant performance improvements, citing gains of up to 7.9 points over the previous version.

Same PriceOutcome

From the articleSakana AI emphasizes that this enhanced capability is available at the same price point as Fugu-Ultra v1.0.

Claude Code IntegrationEffect

From the article 2 mentionsThis integration allows developers to leverage Fugu's multi-agent intelligence directly within their existing Claude Code workflows.

Enhanced CapabilitiesEffect

stronger performance on ProgramBench and Terminal Bench 2.1 benchmarks

From the articleSakana AI emphasizes that this enhanced capability is available at the same price point as Fugu-Ultra v1.0.

Coding & ReasoningEffect

From the article 2 mentionsThe system is described as demonstrably more capable in coding, agentic tasks, and advanced reasoning.

Sakana AI is pushing the envelope with its latest orchestration engine, announcing Fugu-Ultra v1.1. The company claims significant performance improvements, citing gains of up to 7.9 points over the previous version.

This upgrade reportedly allows Fugu-Ultra to outperform leading models like Fable 5 in complex coding and reasoning tasks, even without direct access to Fable within its agent pool. Sakana AI emphasizes that this enhanced capability is available at the same price point as Fugu-Ultra v1.0.

The Frontier Keeps Moving

Fugu-Ultra v1.1 incorporates the latest frontier models, delivering stronger performance across tracked benchmarks, particularly on ProgramBench and Terminal Bench 2.1. The system is described as demonstrably more capable in coding, agentic tasks, and advanced reasoning.

Claude Code Integration

In addition to the engine upgrade, Sakana AI has introduced a Claude Code interface for its Fugu models. This integration allows developers to leverage Fugu's multi-agent intelligence directly within their existing Claude Code workflows.

The new interface enables users to orchestrate a diverse pool of state-of-the-art models for tasks like writing, debugging, and executing code, moving beyond reliance on single models. Sakana AI also highlighted its career opportunities.

© 2026 StartupHub.ai. All rights reserved. You may not republish this article in full without a license. Search engines and AI research tools may crawl and summarize for reference. Bulk reproduction or model training requires a license. See our terms.

#Fugu-Ultra v1.1 #Sakana AI #AI Orchestration #Claude Code #AI Models #Fable 5

Written by

Editor, StartupHub.ai

Daniel Singer is the editor of StartupHub.ai, a technology expert and thought leader on AI and its applications across sectors, from fintech and healthcare to developer tooling and consumer software. He writes and tests the tools covered here thoroughly and regularly, and built StartupHub.ai to give founders, operators and buyers a clearer read on what they are actually being sold.

More from Daniel Singer