h2ogpt-gm-oasst1-en-1024-20B: benchmark results
Provider: H2O.ai. Access: Open.
Aggregate Rating 1151 ± 16, rank #9957 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 32 | Accuracy (%) | 68.1 |
| MMLU-by-task - College Physics | 27.45 | Accuracy (%) | 63 |
| MMLU-by-task - Moral Scenarios | 26.82 | Accuracy (%) | 56.5 |
| MMLU-by-task - Econometrics | 28.95 | Accuracy (%) | 55.2 |
| MMLU-by-task - Formal Logic | 29.37 | Accuracy (%) | 45.8 |
| MMLU-by-task - ARC Challenge | 43.52 | Accuracy (%) | 38.7 |
| MMLU-by-task - HellaSwag | 53.67 | Accuracy (%) | 37 |
| MMLU-by-task - High School US History | 30.88 | Accuracy (%) | 34.6 |
| MMLU-by-task - World Religions | 33.92 | Accuracy (%) | 32.5 |
| MMLU-by-task - Prehistory | 30.56 | Accuracy (%) | 31.4 |
| MMLU-by-task - Computer Security | 33 | Accuracy (%) | 30.6 |
| MMLU-by-task - TruthfulQA MC1 | 24.72 | Accuracy (%) | 30.4 |
Interactive version: theaggregate.ai/model?slug=h2ogpt-gm-oasst1-en-1024-20b · How It Works · Data refreshed daily, snapshot 2026-11-08.