L3.3-MS-Nevoria-70B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1581 ± 31, rank #1238 of 10916 rated models, from 60 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - GPQA47.06Score100
Open LLM Leaderboard - BBH69.98Score98.9
Open LLM Leaderboard - MMLU-Pro55.35Score98.6
Open Japanese LLM - MMLU EN Exact Match81.22Score (%)97.2
Open Japanese LLM - Jemhopqa Char F165.94Score (%)96.9
Open Japanese LLM - Janli Exact Match88.19Score (%)93
Open Japanese LLM - Wikicorpus E TO J Bert Score JA F184.91Score (%)92.1
Open Japanese LLM - Wikicorpus E TO J Bleu JA15.58Score (%)91.1
Open LLM Leaderboard - MuSR46.82Score90.6
Open Japanese LLM - Wikicorpus E TO J Comet Wmt2284.71Score (%)89.8
Open LLM Leaderboard - MATH Level 539.58Score89.7
Open Japanese LLM - RC91.91Score (%)88

Interactive version: theaggregate.ai/model?slug=l3-3-ms-nevoria-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.