Samaya 发布 Sterling 模型，3B 激活参数在金融研究任务超越 Claude Fable 5.1
Samaya AI 推出基于 Nemotron 架构的 Samaya Sterling 模型，通过仅激活 3B 参数实现高效推理。该模型采用“模型与工具协同训练”策略，在 FrontierFinance 基准测试中得分略高于 Claude Fable 5.1，且单次查询成本降低约 11 倍，但存在自报数据及高难度任务表现受限的问题。
报道正文
▲ Marktechpost AI · 2026-10-30 07
▲ Samaya AI just released Samaya Sterling, a 3B-active model that beats Claude Fable 5.1 on financial research.
The key idea is co-training the model with its harness. Sterling is Nemotron 3.5 Lightning (30B MoE, 3B active), post-trained in 4 stages: 2 SFT stages, then offline and online GRPO. A condenser and a compactor keep long research inside a small model's reach.
On FrontierFinance, Sterling scores 58.9% vs 55.9% for Fable 5.1. Cost per question drops from $6.89 to $0.61, about 11x lower. It is a trade-off though: latency is 282 s vs 268 s, the hardest third of questions sits at 45.2%, and all results are self-reported on Samaya's own benchmark....
Full analysis:
