Sakana ships Fugu Max and Fugu Ultra v2, pushing the price-performance Pareto frontier via orchestration
SakanaAILabs · x · 2026-09-11
Sakana AI released Fugu Max and Fugu Ultra v2, two systems built on the same multi-model orchestration architecture. Fugu Max targets price-performance: $2 input / $6 output per 1M tokens, within striking distance of elite models at 2-6x lower cost, with the best overall score on 6 key benchmarks in its tier. Fugu Ultra v2 pushes peak capability: #1 on 5 of 8 hard benchmarks (DeepSWE 74.3; Chartography 48.3 vs Opus 5 at 27.3), achieved without Fable 5, Fable 5.1, or GPT-6-Astra in its agent pool. The thesis: orchestration layers that pick the right machinery per task extend the cost-capability frontier beyond any single model.
More from Models
- New podcast: Meta Muse agent, KV cache deep dive, DeepSeek V4.1 and math drama — altryne · 2026-09-11
- humans& launches Persimmon, first large-scale model to simulate human interaction — xiaosun86 · 2026-09-11
- Tech argument says Anthropic's distillation claim doesn't hold: Kimi and DeepSeek stream reasoning traces in real time — bookwormengr · 2026-09-11
- AGI Society scrutinizes Jensen Huang and Brockman's claims that GPT-6 Astra achieved AGI — bengoertzel · 2026-09-11
- Are Chinese models secretly routing to Claude? A cost and reproducibility rebuttal — op7418 · 2026-09-11
- DeepsecBench security leaderboard: GPT-6 Astra tops at 37.79, Opus 5 costs $128 per run — JohnPhamous · 2026-09-11