Agents
Peak performance across hard benchmarks: • Best or joint-best on 5/8 benchmarks (DeepSWE, Chartography, Toolathon, GDP.pdf, SWEFish) • Chart…
Peak performance across hard benchmarks: • Best or joint-best on 5/8 benchmarks (DeepSWE, Chartography, Toolathon, GDP.pdf, SWEFish) • Chartography: 48.3 (outperforming Opus 5 & Fable 5) • DeepSWE: 74
Peak performance across hard benchmarks: • Best or joint-best on 5/8 benchmarks (DeepSWE, Chartography, Toolathon, GDP.pdf, SWEFish) • Chartography: 48.3 (outperforming Opus 5 & Fable 5) • DeepSWE: 74.3 Achieved without Fable 5, Fable 5.1, or GPT-6-Astra in the agent pool. Details: https://sakana.ai/fugu-max-release/ 🐡
Related
- Fugu Ultra v2 by the numbers. Full Results: https://sakana.ai/fugu-max-release/ • #1 on 5 out of 8 hard benchmarks (including DeepSWE, Chart…
- Our team just shipped Fugu-Ultra v1.1! 🐡 By dynamically orchestrating the latest frontier models, we pushed performance up by 7.9 points. W…
- Fugu Max is now live on @OpenRouter! 🐡 Our learned multi-agent orchestration engine routes tasks across open-weights and specialized models…
Source: David Ha (X) | 2026-09-12