LEDGER - Conversational KPI Lookup: leaderboard
Metric: Recall (%) on 10,000 single-KPI questions over the 494 test annual reports: the model reads a whole OCR-extracted report (about 100k tokens) and returns one requested KPI as JSON (found, value, unit scale, page); a value counts when within 0.05% of the label; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 27B | 91.4 |
| 2 | Ministral 3 14B | 87.9 |
| 3 | GPT-OSS-20B | 85.3 |
Interactive version: theaggregate.ai/benchmark?slug=ledger-conversational-kpi-lookup · How It Works · Data refreshed daily, snapshot 2026-09-29.