Trinity-Nano-Preview — benchmark results

Provider: Arcee AI. Released 2026-01-27. Access: Open.

Unified ELO 1312 ± 16, rank #1508 of 1776 rated models, from 263 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Portuguese NLU - ScaLA PT16.75Linguistic acceptability Score (%)60
EuroEval Spanish NLU - ScaLA ES20.05Linguistic acceptability Score (%)57.9
EuroEval Catalan NLU - ScaLA CA12.14Linguistic acceptability Score (%)57.8
EuroEval Catalan NLU - WikiANN CA64.15Named entity recognition Score (%)54
EuroEval English Knowledge75.33Knowledge Average Score (%)51.8
EuroEval Portuguese NLU - HAREM41.87Named entity recognition Score (%)51.8
Medmarks - MedHallu Hard44.43Score (%)50
EuroEval Bulgarian NLU - MultiWikiQA BG62.06Reading comprehension Score (%)49.8
EuroEval Icelandic NLU - ScaLA IS3.72Linguistic acceptability Score (%)49.2
EuroEval Icelandic NLU - MIM-GOLD NER44.6Named entity recognition Score (%)47.3
EuroEval English NLU - ScaLA EN41.9Linguistic acceptability Score (%)46.2
EuroEval Estonian NLU - EstNER42.21Named entity recognition Score (%)46.2

Interactive version: theaggregate.ai/model?slug=trinity-nano-preview · How the rankings work · Data refreshed daily, snapshot 2026-07-22.