Kev Release - documents-v2 Private Held-Out Test Accuracy: leaderboard
953 private test set; items not public Metric: accuracy.
Metric: accuracy. Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 2 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kev 27B | 0.921 | |
| 2 | Kev 27B v1 | 0.881 |
Interactive version: theaggregate.ai/benchmark?slug=kev-release-documents-v2-private-held-out-test-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-16.