Messier-Opus-14B-Elite7 Benchmark Results

Messier-Opus-14B-Elite7: benchmark results

Provider: prithivMLmods. Access: Open.

Aggregate Rating 1569 ± 34, rank #1411 of 10916 rated models, from 56 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - GPQA	39.09	Score	97.5
Open LLM Leaderboard - MuSR	48.86	Score	96.7
Open LLM Leaderboard - MMLU-Pro	54.04	Score	96.5
Open Japanese LLM - Mbpp Pylint Check	98.19	Score (%)	94.6
Open Japanese LLM - CG	63.45	Score (%)	94
Open LLM Leaderboard - BBH	64.99	Score	91
Open LLM Leaderboard - MATH Level 5	40.71	Score	90.5
Open Japanese LLM - Wiki Coreference SET F1	7.99	Score (%)	86.5
Open LLM Leaderboard - IFEval	71.13	Score	84.4
Open Japanese LLM Leaderboard	65.07	Average Score (%)	83.3
Open Japanese LLM - Xlsum JA Bert Score JA F1	70.14	Score (%)	78.5
Open Japanese LLM - Jemhopqa Char F1	58.77	Score (%)	76.6

Interactive version: theaggregate.ai/model?slug=messier-opus-14b-elite7 · How It Works · Data refreshed daily, snapshot 2026-11-08.