h2o-danube-1.8B-sft: benchmark results
Provider: H2O.ai. Access: Open.
Aggregate Rating 1206 ± 32, rank #9583 of 10916 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 15.09 | Accuracy (%) (5-shot) | 37 |
| Open Portuguese LLM - ASSIN2 RTE | 60.37 | Macro F1 (%) | 21.2 |
| Open Portuguese LLM - ENEM | 23.58 | Accuracy (%) | 20 |
| Open LLM Leaderboard v1 - WinoGrande | 65.43 | Accuracy (%) (5-shot) | 18.8 |
| Open LLM Leaderboard v1 - HellaSwag | 67.34 | Normalized accuracy (%) (10-shot) | 18.3 |
| Open LLM Leaderboard v1 - MMLU | 33.75 | Accuracy (%) (5-shot) | 17.8 |
| Open Portuguese LLM - FaQuAD NLI | 43.97 | Macro F1 (%) | 17.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 40.19 | Normalized accuracy (%) (25-shot) | 16.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.29 | MC2 (%) (0-shot) | 13.6 |
| Open Portuguese LLM - BLUEX | 21.28 | Accuracy (%) | 11.8 |
| Open Portuguese LLM - OAB Exams | 23.83 | Accuracy (%) | 11.3 |
Interactive version: theaggregate.ai/model?slug=h2o-danube-1-8b-sft · How It Works · Data refreshed daily, snapshot 2026-11-08.