Sakana AI Releases Fugu-Ultra v1.1 Upgrade
Enhanced multi-agent AI system dynamically orchestrates frontier models for benchmark gains.
Sakana AI announced Fugu-Ultra v1.1, an upgraded multi-agent system that incorporates the latest frontier models. The release pushes performance up by 7.9 points on complex coding and reasoning tasks, outperforming Fable 5 despite its absence from the agent pool. The Tokyo-based company, founded in 2023, positions collective intelligence as the future. The update is now live at sakana.ai/fugu, building on prior Fugu family reception.
Combined views
102.3K
2 posts, first seen 3h ago
Reactions from ranked influencers
2 posts
Announcing Fugu-Ultra v1.1 🐡 We’ve been thrilled by the reception to the Fugu model family. Thanks to everyone who tried it, shared feedback, and trusted Fugu with real work. Today, we’re releasing Fugu-Ultra v1.1 → https://sakana.ai/fugu Upgraded to incorporate the latest frontier models, resulting in stronger performance across every benchmark shown, including gains of up to 7.9 points over v1.0, with particularly strong results on ProgramBench and Terminal Bench 2.1. Fugu-Ultra v1.1 is more capable across coding, agentic tasks, and advanced reasoning, and available at the same price as Fugu-Ultra v1.0 The frontier keeps moving, and Fugu keeps getting better.
Our team just shipped Fugu-Ultra v1.1! 🐡 By dynamically orchestrating the latest frontier models, we pushed performance up by 7.9 points. We are now beating Fable 5 in complex coding and reasoning tasks without even having Fable 5 in our agent pool. Collective intelligence is the future.
Announcing Fugu-Ultra v1.1 🐡 We’ve been thrilled by the reception to the Fugu model family. Thanks to everyone who tried it, shared feedback, and trusted Fugu with real work. Today, we’re releasing Fugu-Ultra v1.1 → https://sakana.ai/fugu Upgraded to incorporate the latest frontier models, resulting in stronger performance across every benchmark shown, including gains of up to 7.9 points over v1.0, with particularly strong results on ProgramBench and Terminal Bench 2.1. Fugu-Ultra v1.1 is more capable across coding, agentic tasks, and advanced reasoning, and available at the same price as Fugu-Ultra v1.0 The frontier keeps moving, and Fugu keeps getting better.