h2ogpt-gm-oasst1-multilang-1024-20B: benchmark results
Provider: H2O.ai. Access: Open.
Aggregate Rating 1152 ± 16, rank #9948 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Physics | 34.31 | Accuracy (%) | 86.4 |
| MMLU-by-task - High School Physics | 32.45 | Accuracy (%) | 66 |
| MMLU-by-task - Moral Scenarios | 24.8 | Accuracy (%) | 41.6 |
| MMLU-by-task - ARC Challenge | 43.69 | Accuracy (%) | 39 |
| MMLU-by-task - HellaSwag | 53.5 | Accuracy (%) | 36.7 |
| MMLU-by-task - High School US History | 31.37 | Accuracy (%) | 35.1 |
| MMLU-by-task - World Religions | 34.5 | Accuracy (%) | 33.2 |
| MMLU-by-task - Electrical Engineering | 30.34 | Accuracy (%) | 32.9 |
| MMLU-by-task - Moral Disputes | 30.35 | Accuracy (%) | 32.5 |
| MMLU-by-task - Astronomy | 30.92 | Accuracy (%) | 32.4 |
| MMLU-by-task - Computer Security | 35 | Accuracy (%) | 32.3 |
| MMLU-by-task - High School World History | 29.96 | Accuracy (%) | 31.6 |
Interactive version: theaggregate.ai/model?slug=h2ogpt-gm-oasst1-multilang-1024-20b · How It Works · Data refreshed daily, snapshot 2026-11-08.