FrontierFinance: 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) | 55.86 |
| 2 | Claude Fable 5 (High) | 49.19 |
| 3 | GPT-5.6 Sol (Medium) | 46.83 |
| 4 | Kimi K3 (Max) | 46.37 |
| 5 | Gemini 3.6 Flash (Medium) | 46.27 |
| 6 | Claude Opus 4.8 (High) | 45.04 |
| 7 | GPT-5.5 (Medium) | 43.47 |
| 8 | GLM-5.2 (Max) | 42.77 |
| 9 | DeepSeek V4 Pro (High) | 40.54 |
| 10 | Kimi K2.6 | 32.32 |
| 11 | Gemini 3.1 Pro (Preview) (High) | 30.51 |
Interactive version: theaggregate.ai/benchmark?slug=frontierfinance · How It Works · Data refreshed daily, snapshot 2026-09-26.