FrontierFinance - Company Research: leaderboard
Metric: Rubric qualification rate (%, macro average over queries, three-judge majority vote). Source: research.samaya.ai. Saturation forecast: Around 2029. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5.1 (High) | 53.71 |
| 2 | Kimi K3 (Max) | 45.91 |
| 3 | GPT-5.6 Sol (Medium) | 42.15 |
| 4 | Gemini 3.6 Flash (Medium) | 41.16 |
| 5 | Claude Fable 5 (High) | 40.54 |
| 6 | GPT-5.5 (Medium) | 39.67 |
| 7 | Claude Opus 4.8 (High) | 38.93 |
| 8 | GLM-5.2 (Max) | 38.52 |
| 9 | Kimi K2.6 | 33.3 |
| 10 | DeepSeek V4 Pro (High) | 32.08 |
| 11 | Gemini 3.1 Pro (Preview) (High) | 29.09 |
Interactive version: theaggregate.ai/benchmark?slug=frontierfinance-company-research · How It Works · Data refreshed daily, snapshot 2026-09-26.