LinMix - OLMo2 1B 288 Domains - hellaswagpiqa Accuracy: leaderboard
LinMix compares separately trained, publicly released language models built from scratch with different training-data mixtures. Each result belongs to its exact trained checkpoint; lower bits per byte is better. Accuracy (%).
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | LinMix olmo2-1B-288domains-vertex-linear-hellaswagpiqa | 69 | |
| 2 | LinMix olmo2-1B-288domains-dirichlet-exponential-hellaswagpiqa | 64.1 | |
| 3 | LinMix olmo2-1B-288domains-dirichlet-lightgbm-hellaswagpiqa | 63.8 | |
| 4 | LinMix olmo2-1B-288domains-baseline | 63.4 |
Interactive version: theaggregate.ai/benchmark?slug=linmix-olmo2-1b-288-domains-hellaswagpiqa-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-29.