Qwen2.5-14B-Ultimav2: benchmark results
Provider: CultriX. Access: Open.
Aggregate Rating 1575 ± 34, rank #1324 of 10916 rated models, from 56 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 49.66 | Score | 97.8 |
| Open LLM Leaderboard - MMLU-Pro | 54.17 | Score | 97.3 |
| Open LLM Leaderboard - GPQA | 38.51 | Score | 96.2 |
| Open LLM Leaderboard - BBH | 65.55 | Score | 93.2 |
| Open LLM Leaderboard - MATH Level 5 | 38.44 | Score | 88.8 |
| Open Japanese LLM - Wiki Coreference SET F1 | 7.9 | Score (%) | 85.5 |
| Open Japanese LLM - CG | 58.63 | Score (%) | 84.4 |
| Open Japanese LLM - Mbpp Pylint Check | 94.38 | Score (%) | 84.1 |
| Open Japanese LLM - ALT E TO J Comet Wmt22 | 90.89 | Score (%) | 79.9 |
| Open Japanese LLM - MT | 84.78 | Score (%) | 79.2 |
| Open Japanese LLM - Commonsensemoralja Exact Match | 90.53 | Score (%) | 78.4 |
| Open Japanese LLM - EL | 57.72 | Score (%) | 78.4 |
Interactive version: theaggregate.ai/model?slug=qwen2-5-14b-ultimav2 · How It Works · Data refreshed daily, snapshot 2026-11-08.