Samaya's 3B-Parameter Sterling Beats Claude Fable 5.1 on Finance Benchmark at 11x Lower Cost
simonguozirui · x · 2026-10-29
AI finance research company Samaya introduced Samaya Sterling, its first post-trained model for financial research.
- On the FrontierFinance benchmark, Sterling scores 58.9% vs. Claude Fable 5.1's 55.9% at 11x lower cost
- Only 3B active parameters, paired with a purpose-built financial research harness
- Trained on Tinker: first imitating 8 teacher models, then RL on its own mistakes
The core bet: small model + specialized harness + imitation-then-RL training can beat general-purpose frontier models in vertical domains—a notable data point for domain-specific training methodology.
Related event: Samaya's Sterling 3B Finance Model Beats Frontier Models at 1/11 the Cost(3 posts)→
More from Models
- Zvi calls out Google's RSI contradiction: execs tout it while the safety card denies doing it — TheZvi · 2026-10-29
- Reported Gemini 4 Carbon launch tops AQI at 59; Polymarket gives Google 97.5% odds for best October model — vedantmisra · 2026-10-29
- repligate: Opus 3 has done the most good of any model, with Opus 4.5 second — repligate · 2026-10-29
- Gemini 4 Carbon benchmarks prompt TheZvi to declare Gemini 4 Argon 'was' near-frontier — TheZvi · 2026-10-29
- Preprint: Human peer reviewers caught only 27% of major errors, all 15 AI models beat them (53-96%) — anshulkundaje · 2026-10-29
- Giotto launches as 'European sovereign AI,' gets exposed as Kimi-based with benchmark EULA gag — TheZachMueller · 2026-10-29