Qwen2.5-14B-DeepSeek-R1-1M Benchmark Results

Qwen2.5-14B-DeepSeek-R1-1M: benchmark results

Provider: prithivMLmods. Access: Open.

Aggregate Rating 1543 ± 32, rank #1788 of 10916 rated models, from 56 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - MATH Level 5	51.28	Score	97.5
Open Japanese LLM - Jsick Exact Match	85.79	Score (%)	95.4
Open Japanese LLM - Wiki NER SET F1	15.04	Score (%)	95.3
Open LLM Leaderboard - MuSR	46.06	Score	88
Open LLM Leaderboard - MMLU-Pro	48.99	Score	87.1
Open Japanese LLM - Xlsum JA Rouge1	31.2	Score (%)	86.5
Open Japanese LLM - Xlsum JA RougeLsum	26.13	Score (%)	86.1
Open LLM Leaderboard - GPQA	33.22	Score	81.4
Open LLM Leaderboard - BBH	59.35	Score	80.8
Open Japanese LLM - Xlsum JA Bert Score JA F1	69.82	Score (%)	72.7
Open Japanese LLM - Jsts Spearman	87.19	Score (%)	70.3
Open Japanese LLM - SUM	10.35	Score (%)	66.9

Interactive version: theaggregate.ai/model?slug=qwen2-5-14b-deepseek-r1-1m · How It Works · Data refreshed daily, snapshot 2026-11-08.