h2ogpt-oasst1-512-12B: benchmark results
Provider: H2O.ai. Access: Open.
Aggregate Rating 1148 ± 16, rank #9995 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Mathematics | 28.52 | Accuracy (%) | 64.7 |
| MMLU-by-task - Econometrics | 28.07 | Accuracy (%) | 47.3 |
| MMLU-by-task - High School Chemistry | 30.05 | Accuracy (%) | 40.5 |
| MMLU-by-task - Elementary Mathematics | 26.98 | Accuracy (%) | 39.2 |
| MMLU-by-task - HellaSwag | 52.26 | Accuracy (%) | 34.4 |
| MMLU-by-task - ARC Challenge | 40.27 | Accuracy (%) | 34.3 |
| MMLU-by-task - International Law | 40.5 | Accuracy (%) | 34.2 |
| MMLU-by-task - Human Aging | 38.12 | Accuracy (%) | 34 |
| MMLU-by-task - Anatomy | 34.07 | Accuracy (%) | 33.8 |
| MMLU-by-task - College Biology | 30.56 | Accuracy (%) | 33.8 |
| MMLU-by-task - Astronomy | 31.58 | Accuracy (%) | 33.7 |
| MMLU-by-task - Professional Psychology | 28.59 | Accuracy (%) | 32.1 |
Interactive version: theaggregate.ai/model?slug=h2ogpt-oasst1-512-12b · How It Works · Data refreshed daily, snapshot 2026-11-08.