FrontierFinance v3.1 — Factual Data Extraction Rubrics
Professional Work · 2026-07-06
Factual Data Extraction rubric-category slice in the official FrontierFinance v3.1 system breakdown, with a reported denominator of 8,547 rubric criteria. It reports micro-averaged rubric qualification rate within that displayed category.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5.1 | 44.5 |
| Claude Fable 5 | 43.1 |
| GPT-5.5 | 38.3 |
| Opus 4.8 | 38.3 |
| Gemini 3.8 Flash | 38.2 |
| Gemini 3.6 Flash | 38.0 |
| GPT-5.6 Sol | 35.7 |
| Kimi K2.6 | 30.6 |
| DeepSeek-V4-Pro | 30.2 |
| Kimi K3 | 29.7 |
| GLM-5.2 | 28.7 |
| Ling 3.0 Flash Fin | 28.4 |
| Gemini 3.1 Pro Preview | 20.2 |