h2o-danube3.1-4B-chat: benchmark results
Provider: H2O.ai. Access: Open.
Unified ELO 1408 ± 58, rank #1840 of 2656 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 50.21 | Score | 59.3 |
| Open LLM Leaderboard - MuSR | 41.02 | Score | 50.6 |
| Open Portuguese LLM - FaQuAD NLI | 57.59 | Macro F1 (%) | 41 |
| Open LLM Leaderboard - GPQA | 28.52 | Score | 40.2 |
| Open Portuguese LLM - ENEM | 52.9 | Accuracy (%) | 36.3 |
| Open Portuguese LLM - OAB Exams | 37.31 | Accuracy (%) | 35.4 |
| Open Portuguese LLM - BLUEX | 39.08 | Accuracy (%) | 32.1 |
| Open LLM Leaderboard - MMLU-Pro | 27.19 | Score | 29.2 |
| Open Portuguese LLM - ASSIN2 RTE | 75.79 | Macro F1 (%) | 27.7 |
| Open LLM Leaderboard - BBH | 36.08 | Score | 20.6 |
| Open LLM Leaderboard - MATH Level 5 | 3.32 | Score | 20.2 |
Interactive version: theaggregate.ai/model?slug=h2o-danube3-1-4b-chat · How It Works · Data refreshed daily, snapshot 2026-09-19.