Model Release

Sakana AI's Fugu Orchestrate Multiple LLMs to Match Anthropic Benchmarks

Sakana AI's Fugu outperforms Anthropic's Fable 5 and Mythos Preview in benchmarks, despite not using those models in its pool. The system is available in two variants.

A mysterious silhouette with red binary code projected over the face, set against a dark, moody background.

Photo: cottonbro studio / Pexels

Sakana AI has launched Fugu, a multi-LLM orchestrator that behaves like a single model through one API. Fugu dynamically coordinates multiple language models from a swappable pool to tackle complex tasks. The system is available in two variants: a base version for everyday use and a more powerful Fugu Ultra for complex, multi-step problems. According to benchmark results, Fugu Ultra performs on par with Anthropic's Fable 5 and Mythos Preview across coding, reasoning, science, and agent benchmarks. The system is designed to reduce dependence on any single AI provider. Sakana AI claims its LLM orchestrator Fugu sets new benchmark highs, beating Anthropic's Fable 5 and Mythos 5. | Image: Sakana AI

Fugu is itself a language model trained to call other LLMs from an agent pool, including copies of itself. Depending on the request, it either handles a task on its own or pulls together a team of specialized models. Selection, delegation, checks, and synthesis all run internally. Users access everything through a single OpenAI-compatible API. The system's real-world performance depends entirely on which models are in the pool, though. If several top providers restrict access at the same time, Fugu's options shrink too. An orchestrator like Fugu may boost resilience, but it's not the same as true sovereignty. Still, Fugu could be worth watching on raw performance alone. How much the orchestration drives up token usage and costs remains an open question that Sakana doesn't address in its announcement.

Sakana AI is pitching Fugu as a safeguard against single-provider dependence. The company points to the recent export controls on Anthropic's Fable and Mythos models as a concrete example. Access to top AI systems can vanish overnight due to regulatory shifts or foreign policy decisions. 'For an organization or a nation, relying on a single company’s APIs for critical infrastructure, finance, or governance is a material vulnerability. This risk is no longer a hypothetical possibility, but a reality,' Sakana AI writes in its announcement. Fugu's model pool is fully swappable, so the system can reroute to other models if one provider goes dark. Both variants are live now through a single API on the product page and console. Sakana offers subscription plans for daily use and usage-based billing for bigger workloads. Source: thedecoder

Key points

Sakana AI's Fugu outperforms Anthropic's Fable 5 and Mythos Preview in benchmarks, despite not using those models in its pool.
Fugu is available in two variants: a base version for everyday use and a more powerful Fugu Ultra for complex, multi-step problems.
Fugu dynamically coordinates multiple language models from a swappable pool to tackle complex tasks.
Sakana AI claims its LLM orchestrator Fugu sets new benchmark highs, beating Anthropic's Fable 5 and Mythos 5.
Fugu's model pool is fully swappable, so the system can reroute to other models if one provider goes dark.
Sakana AI is pitching Fugu as a safeguard against single-provider dependence.
Both variants are live now through a single API on the product page and console.

Source: The Decoder Read the original →

WRITTEN BY

Alex Lindgren

LLMs & Frontier Models

Alex covers the large language models and their impact on society.