T3Q-qwen2.5-14B-v1.2-e2: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1547 ± 35, rank #1734 of 10916 rated models, from 50 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - Jsick Exact Match85.51Score (%)93.4
Open Japanese LLM - CG61.65Score (%)90.5
Open Japanese LLM - Jamp Exact Match69.25Score (%)86.8
Open Japanese LLM - Jsts Pearson90.12Score (%)82.7
Open Japanese LLM - Wiki Dependency SET F139.14Score (%)82.2
Open Japanese LLM - Mbpp Pylint Check91.57Score (%)79.2
Open Japanese LLM - NLI78.62Score (%)79.1
Open Japanese LLM Leaderboard64.67Average Score (%)77.6
Open Japanese LLM - Wikicorpus J TO E Bert Score EN F190.62Score (%)77.3
Open Japanese LLM - ALT E TO J Comet Wmt2290.82Score (%)75.8
Open Japanese LLM - Wikicorpus J TO E Bleu EN11.36Score (%)75.2
Open Japanese LLM - Jcommonsenseqa Exact Match95.44Score (%)74.3

Interactive version: theaggregate.ai/model?slug=t3q-qwen2-5-14b-v1-2-e2 · How It Works · Data refreshed daily, snapshot 2026-11-08.