FrontierFinance - Screening & Discovery: leaderboard
Metric: Rubric qualification rate (%, macro average over queries, three-judge majority vote). Source: research.samaya.ai. Saturation forecast: Around 2030. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5.1 (High) | 39.85 |
| 2 | Kimi K3 (Max) | 36.89 |
| 3 | GPT-5.6 Sol (Medium) | 36.52 |
| 4 | Gemini 3.6 Flash (Medium) | 36.11 |
| 5 | GPT-5.5 (Medium) | 34.78 |
| 6 | Claude Fable 5 (High) | 33.28 |
| 7 | Claude Opus 4.8 (High) | 30.17 |
| 8 | DeepSeek V4 Pro (High) | 28.05 |
| 9 | Kimi K2.6 | 27.83 |
| 10 | GLM-5.2 (Max) | 24.86 |
| 11 | Gemini 3.1 Pro (Preview) (High) | 21.55 |
Interactive version: theaggregate.ai/benchmark?slug=frontierfinance-screening-discovery · How It Works · Data refreshed daily, snapshot 2026-09-26.