Sakana: Fugu Max
sakana's flagship model. Long-context specialist with 1M window.
Scores by test
Methodology →What you need to know
Sakana: Fugu Max is a high-performance model optimized for complex reasoning and long-form context. With a 1M token context window and a 4.77/5.0 average internal score, it ranks in the top 8 percent of 164 models. Its primary technical advantage lies in high-order cognitive tasks, specifically strategic analysis, agentic planning, and creative problem solving, all of which achieved perfect scores.
The model maintains consistent reliability across diverse tasks, including faithfulness, multilingual support, and tabular data processing. While it is highly capable, its relative weaknesses are in structured output, tool calling, and classification. However, these are minor deficits, as the model still scores 4/5 in these areas, indicating a baseline of competence rather than a failure point.
At a blended cost of $5.00 per million tokens, this model sits at a premium price point. Developers are paying for top-tier reasoning capabilities and an expansive context window rather than cost efficiency. The pricing is aligned with its rank as a top-15 model, making it a viable option for high-stakes enterprise applications where accuracy outweighs per-token overhead.
Use this model if your project requires deep strategic analysis, complex agentic workflows, or processing massive datasets within a single prompt. Skip this model if you are building a simple classification tool or a high-volume API where cost-per-token is the primary constraint.
Strengths — Top 3
Relative weaknesses — Bottom 3
Similar models