magnum-v3-9B-chatml: benchmark results
Provider: Other. Access: Open.
Unified ELO 1515 ± 59, rank #1006 of 2656 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - ENEM | 74.39 | Accuracy (%) | 86.9 |
| Open LLM Leaderboard - GPQA | 34.56 | Score | 86.3 |
| Open Portuguese LLM - BLUEX | 65.23 | Accuracy (%) | 86.2 |
| Open Portuguese LLM - OAB Exams | 54.4 | Accuracy (%) | 86.1 |
| Open LLM Leaderboard - MuSR | 44.32 | Score | 79.8 |
| Open LLM Leaderboard - MMLU-Pro | 42.42 | Score | 77.1 |
| Open LLM Leaderboard - BBH | 54.28 | Score | 70.1 |
| Open Portuguese LLM - ASSIN2 RTE | 87.88 | Macro F1 (%) | 42.5 |
| Open LLM Leaderboard - MATH Level 5 | 6.95 | Score | 37.2 |
| Open Portuguese LLM - FaQuAD NLI | 51.29 | Macro F1 (%) | 32.8 |
| Open LLM Leaderboard - IFEval | 12.75 | Score | 2.9 |
Interactive version: theaggregate.ai/model?slug=magnum-v3-9b-chatml · How It Works · Data refreshed daily, snapshot 2026-09-19.