# 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._
**Published:** 2026-07-24
**Source:** https://www.startuphub.ai/ai-news/technology/2026/sakana-fugu-ultra-v1-1-boosts-ai-performance
---
Sakana AI is pushing the envelope with its latest orchestration engine, announcing [Fugu-Ultra v1.1](https://sakana.ai/fugu-1-1-claude-code-interface/). The company claims significant performance improvements, citing gains of up to 7.9 points over the previous version.

Sakana AICore

company pushing AI performance with new orchestration engineFrom the article 4 mentionsSakana AI is pushing the envelope with its latest orchestration engine, announcing Fugu-Ultra v1.1.releasesFugu-Ultra v1.1Corenew orchestration engine with significant performance improvements over previous versionFrom 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 GainsEffectup to 7.9 points gain, outperforming Fable 5 in complex tasksFrom the article 2 mentionsThe company claims significant performance improvements, citing gains of up to 7.9 points over the previous version.Same PriceOutcomeFrom the articleSakana AI emphasizes that this enhanced capability is available at the same price point as Fugu-Ultra v1.0.Claude Code IntegrationEffectFrom the article 2 mentionsThis integration allows developers to leverage Fugu's multi-agent intelligence directly within their existing Claude Code workflows.leading toEnhanced CapabilitiesEffectstronger performance on ProgramBench and Terminal Bench 2.1 benchmarksFrom the articleSakana AI emphasizes that this enhanced capability is available at the same price point as Fugu-Ultra v1.0.improvingCoding & ReasoningEffectFrom the article 2 mentionsThe system is described as demonstrably more capable in coding, agentic tasks, and advanced reasoning.
This upgrade reportedly allows Fugu-Ultra to outperform leading models like [Fable 5](https://sakana.ai/fugu-1-1-claude-code-interface/) 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](https://sakana.ai/fugu-1-1-claude-code-interface/) 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](https://sakana.ai/fugu-1-1-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](https://sakana.ai/fugu-1-1-claude-code-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.
---
Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory.