Qwen2.5-14B-Vimarckoso-v3: benchmark results
Provider: Alibaba. Access: Open.
Aggregate Rating 1569 ± 32, rank #1413 of 10916 rated models, from 61 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - ASSIN2 RTE | 94.4 | Macro F1 (%) | 96.2 |
| Open Portuguese LLM - BLUEX | 73.99 | Accuracy (%) | 95 |
| Open LLM Leaderboard - MuSR | 48.07 | Score | 94.9 |
| Open LLM Leaderboard - GPQA | 38 | Score | 94.8 |
| Open LLM Leaderboard - MMLU-Pro | 53.43 | Score | 93.7 |
| Open Portuguese LLM - OAB Exams | 61.41 | Accuracy (%) | 93.6 |
| Open Portuguese LLM - ENEM | 79.36 | Accuracy (%) | 92.7 |
| Open Japanese LLM - CG | 62.25 | Score (%) | 91.5 |
| Open Portuguese LLM - FaQuAD NLI | 80.59 | Macro F1 (%) | 90.3 |
| Open LLM Leaderboard - MATH Level 5 | 40.03 | Score | 90.1 |
| Open Japanese LLM - Wiki Coreference SET F1 | 8.4 | Score (%) | 89.7 |
| Open LLM Leaderboard - BBH | 64.15 | Score | 88.9 |
Interactive version: theaggregate.ai/model?slug=qwen2-5-14b-vimarckoso-v3 · How It Works · Data refreshed daily, snapshot 2026-11-08.