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
- Magic Patterns' first engineer: Cursor in Slack, a Patterson review agent, repo clones over worktrees — Y Combinator Blog · 2026-10-28
- Dev builds AI job-search app for his wife, she lands a job, and he open-sources it — CurieuxExplorer · 2026-10-28
- Supercharging LLM classification with logprobs: soft classifiers you can threshold-tune — JnBrymn · 2026-10-28
- Codex daily build series day 23: skipping iCloud plugins for a reset — dotey · 2026-10-28
- Cloudflare Access adds fully customizable pages with HTML + Liquid templates — dinasaur_404 · 2026-10-28
- Opus retried every session 20.6 million times during a memory leak hunt — johnlindquist · 2026-10-28