h2ogpt-oasst1-512-20B: benchmark results
Provider: H2O.ai. Access: Open.
Aggregate Rating 1152 ± 16, rank #9936 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Mathematics | 27.04 | Accuracy (%) | 50.6 |
| MMLU-by-task - Elementary Mathematics | 28.04 | Accuracy (%) | 46.6 |
| MMLU-by-task - Formal Logic | 29.37 | Accuracy (%) | 45.8 |
| MMLU-by-task - Moral Scenarios | 24.69 | Accuracy (%) | 38.9 |
| MMLU-by-task - ARC Challenge | 43.09 | Accuracy (%) | 38 |
| MMLU-by-task - HellaSwag | 53.72 | Accuracy (%) | 37.2 |
| MMLU-by-task - Business Ethics | 37 | Accuracy (%) | 36 |
| MMLU-by-task - Anatomy | 34.81 | Accuracy (%) | 34.9 |
| MMLU-by-task - Astronomy | 32.24 | Accuracy (%) | 34.7 |
| MMLU-by-task - Abstract Algebra | 27 | Accuracy (%) | 34 |
| MMLU-by-task - Computer Security | 37 | Accuracy (%) | 33.9 |
| MMLU-by-task - Jurisprudence | 32.41 | Accuracy (%) | 33.7 |
Interactive version: theaggregate.ai/model?slug=h2ogpt-oasst1-512-20b · How It Works · Data refreshed daily, snapshot 2026-11-08.