h2o-danube2-1.8B-base: benchmark results
Provider: H2O.ai. Access: Open.
Unified ELO 1335 ± 21, rank #2566 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 29.8 | Accuracy (%) (5-shot) | 47 |
| Open Portuguese LLM - BLUEX | 28.37 | Accuracy (%) | 24.2 |
| Open LLM Leaderboard v1 - HellaSwag | 72.95 | Normalized accuracy (%) (10-shot) | 23.4 |
| Open Portuguese LLM - ENEM | 27.15 | Accuracy (%) | 22.3 |
| Open LLM Leaderboard v1 - WinoGrande | 68.03 | Accuracy (%) (5-shot) | 22.2 |
| Open Portuguese LLM - ASSIN2 RTE | 62.92 | Macro F1 (%) | 22 |
| Open LLM Leaderboard v1 - MMLU | 40.2 | Accuracy (%) (5-shot) | 21.2 |
| Open Portuguese LLM - OAB Exams | 26.65 | Accuracy (%) | 20 |
| Open LLM Leaderboard v1 - ARC Challenge | 43.34 | Normalized accuracy (%) (25-shot) | 19.2 |
| Open Portuguese LLM - FaQuAD NLI | 43.97 | Macro F1 (%) | 17.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 38.01 | MC2 (%) (0-shot) | 7.1 |
Interactive version: theaggregate.ai/model?slug=h2o-danube2-1-8b-base · How It Works · Data refreshed daily, snapshot 2026-09-23.