mamba-2.8B-hf — benchmark results

Provider: Other. Released 2024-03-05. Access: Open.

Unified ELO 1249 ± 20, rank #1620 of 1776 rated models, from 11 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Dutch NLU - DBRD69.95Sentiment classification Score (%)27.4
EuroEval Portuguese NLU - SST-2 PT58.23Sentiment classification Score (%)22.7
EuroEval Portuguese NLU - ScaLA PT1.62Linguistic acceptability Score (%)22.7
EuroEval Dutch NLU - SQuAD NL34.26Reading comprehension Score (%)21
EuroEval Portuguese NLU - MultiWikiQA PT26.85Reading comprehension Score (%)19.6
EuroEval Portuguese Common Sense Reasoning0.87Common Sense Reasoning Average Score (%)15.1
EuroEval Portuguese NLU25.84NLU Average Score (%)15
EuroEval Portuguese17.28Average Score (%)12.2
BABILong (NIAH)33.2Avg Accuracy (%)10.3
EuroEval Portuguese NLU - HAREM16.66Named entity recognition Score (%)9.2
EuroEval Portuguese Knowledge-0.55Knowledge Average Score (%)4.6

Interactive version: theaggregate.ai/model?slug=mamba-2-8b-hf · How the rankings work · Data refreshed daily, snapshot 2026-07-22.