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

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MuSR49.66Score97.8
Open LLM Leaderboard - MMLU-Pro54.17Score97.3
Open LLM Leaderboard - GPQA38.51Score96.2
Open LLM Leaderboard - BBH65.55Score93.2
Open LLM Leaderboard - MATH Level 538.44Score88.8
Open Japanese LLM - Wiki Coreference SET F17.9Score (%)85.5
Open Japanese LLM - CG58.63Score (%)84.4
Open Japanese LLM - Mbpp Pylint Check94.38Score (%)84.1
Open Japanese LLM - ALT E TO J Comet Wmt2290.89Score (%)79.9
Open Japanese LLM - MT84.78Score (%)79.2
Open Japanese LLM - Commonsensemoralja Exact Match90.53Score (%)78.4
Open Japanese LLM - EL57.72Score (%)78.4

Interactive version: theaggregate.ai/model?slug=qwen2-5-14b-ultimav2 · How It Works · Data refreshed daily, snapshot 2026-11-08.