Kev Release - ood-v2 Test ECE: leaderboard

4988 / 2084 / 4949 Kev-27B card: "held-out domains of generators that also produced training data … Gains there measure held-out items of trained families, not transfer to new tasks." Metric: ECE.

Metric: ECE. Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 3 models tracked. Updated 14 Nov 2026.

Top models

#ModelScoreOverall rank
1Kev 27B0.02
2Kev 27B v10.044
3Kev 4B0.084

Interactive version: theaggregate.ai/benchmark?slug=kev-release-ood-v2-test-ece · How It Works · Data refreshed daily, snapshot 2026-11-16.