# Samaya trains Nemotron 3.5 Lightning to beat Fable 5.1 at 9% cost

> Original title: Samaya trained Nemotron 3.5 Lightning to beat Fable 5.1 on its finance research benchmark at 9% of the cost. The model was trained on Tin...

- Source: Tinker
- Published: 2026-10-28T17:33:33.000Z
- Bad Influence: https://badinfluence.news/items/pe10z5nbj8kw7d2efihsqlndg
- Original: https://x.com/tinkerapi/status/2115497211119456599

## Summary

Samaya trained Nemotron 3.5 Lightning on Tinker to beat Fable 5.1 on its finance research benchmark at 9% of the cost. Training combined imitation of 8 teachers with reinforcement learning on the model's own mistakes, along with the harness it runs in. Samaya's companion post says its Sterling model scores 58.9% against Fable 5.1's 55.9% on FrontierFinance at 11 times lower cost.

## Post

Samaya trained Nemotron 3.5 Lightning to beat Fable 5.1 on its finance research benchmark at 9% of the cost. The model was trained on Tinker together with the harness it works in: first by imitating 8 teachers, then RL on its own mistakes.

## Quoted post @samaya_AI

> Introducing Samaya Sterling: our first post-trained model for state-of-the-art financial research.
> 
> On FrontierFinance, Sterling outperforms Claude Fable 5.1 (58.9% vs. 55.9%) at 11× lower cost.
> 
> Using a model with just 3B active parameters, Sterling demonstrates what's possible when specialized training meets a purpose-built financial research harness.
> 
> Read the full research ↓

https://x.com/samaya_AI/status/2115480443307041130