FrontierFinance - Samaya Sterling Harness: leaderboard
Samaya Sterling answers 220 held-out FrontierFinance financial research questions with its co-adapted research harness, financial tools, context condenser and compactor, and separate report writer. The score is the mean share of expert rubric items satisfied (%); higher is better. Default and High research budgets use the same trained checkpoint; the High result averages two runs. These model-and-harness results remain separate from Finance Agent v2 and web-search baseline runs.
Metric: Rubric qualification rate (%). Source: research.samaya.ai. Saturation forecast: Rough model projection: around 2026. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Samaya Sterling (High) | 60.6 | |
| 2 | Samaya Sterling | 58.9 |
Interactive version: theaggregate.ai/benchmark?slug=frontierfinance-samaya-sterling-harness · How It Works · Data refreshed daily, snapshot 2026-11-05.