Sakana launches Fugu Max and Ultra v2, topping 5 of 8 hard benchmarks via multi-agent orchestration
SakanaAILabs · x · 2026-09-11
Sakana AI released Fugu Max and Fugu Ultra v2, new versions of its multi-agent orchestration system built around the idea that the real frontier is the capability-cost Pareto frontier, not ever-bigger single models.
- One architecture, two missions: Fugu Max maximizes output quality per dollar; Fugu Ultra v2 maximizes peak capability on complex multi-step tasks without indispensable reliance on the frontier models it orchestrates.
- Results: Ultra v2 ranks #1 on 5 of 8 hard benchmarks, scoring 74.3 on DeepSWE and 48.3 on Chartography versus Opus 5's 27.3 — achieved without Fable 5, Fable 5.1, or GPT-6-Astra in the agent pool.
- Trajectory: From April beta to June GA with Ultra v1, Fugu has grown into an enterprise-grade orchestration engine with the largest pool of open and specialized models to date.
More from coding & agent
- One Dollar Audit Offers AI Smart Contract Security Audits for $1 on Base — seanwbren · 2026-09-11
- SWE-Together Update: Claude Fable 5 Tops Coding Benchmark, Muse Spark 1.3 Is 5x Cheaper — shuchaobi · 2026-09-11
- GPT-6 Astra 3D Workflow: Blender MCP for Hard-Surface, TripoAI for Organic Models — majidmanzarpour · 2026-09-11
- Gemini Canvas Turns Any Google Sheet Into an App, Sparking Startup-Killing Concerns — VishnuNath · 2026-09-11
- Developer asks how to turn real codebases into instruction-to-code fine-tuning datasets — ImBadGuyInEveryStory · 2026-09-11
- Sierra Catalina proposes Context Layer: a six-step user-controlled protocol for sharing minimal context across AI agents — sierracatalina · 2026-09-11