QwenSlerp2-14B: benchmark results

Provider: Alibaba.

Aggregate Rating 1553 ± 32, rank #1667 of 10916 rated models, from 55 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - CG64.26Score (%)95.8
Open Portuguese LLM - ASSIN2 RTE94.32Macro F1 (%)95.8
Open Portuguese LLM - OAB Exams62.82Accuracy (%)95.4
Open Portuguese LLM - BLUEX73.57Accuracy (%)94.6
Open Portuguese LLM - ENEM80.76Accuracy (%)94.4
Open Japanese LLM - Mbpp Pylint Check97.39Score (%)91.8
Open Portuguese LLM - FaQuAD NLI80.22Macro F1 (%)89.5
Open Japanese LLM - Wiki Coreference SET F18.21Score (%)88.2
Open Japanese LLM - Jsick Exact Match82.69Score (%)78.7
Open Japanese LLM Leaderboard64.65Average Score (%)76.7
Open Japanese LLM - Xlsum JA Bleu JA2.91Score (%)75.8
Open Japanese LLM - Wiki Dependency SET F137.7Score (%)74.3

Interactive version: theaggregate.ai/model?slug=qwenslerp2-14b · How It Works · Data refreshed daily, snapshot 2026-11-08.