Marco De Rossi(@marco_derossi):On JevBench, Sage1 scores better on accuracy than other System1 models, with a similar median latency. When multi-step reasoning is required, Sage has 93% accuracy vs. 71% for other System1 models. Sage is smart enough to know when to be fast and when to think step by step, covering both System1 and System2. When Sage activates reasoning, it takes on average 3X longer to decide.

Marco De Rossi

@marco_derossi

CEO, @LevantoLabs 🤖 AI Lead, @MetaMask 🦊 Pioneered MOOCs, LMS, Web3 tooling, agentic coordination (ERC-8004) and now decision models · 2 exits

가입 January 2012

1.8K 팔로잉 중 6.7K 팬

Marco De Rossi@marco_derossi

2026.09.23 17:15

On JevBench, Sage1 scores better on accuracy than other System1 models, with a similar median latency. When multi-step reasoning is required, Sage has 93% accuracy vs. 71% for other System1 models. Sage is smart enough to know when to be fast and when to think step by step, covering both System1 and System2. When Sage activates reasoning, it takes on average 3X longer to decide.