Apertus-8B-Instruct-2509 — benchmark results

Swiss AI Initiative's (ETH Zurich/EPFL/CSCS) open 8B sibling of Apertus-70B, pretrained on 15T tokens of compliant open data in 1,811 languages (September 2025). Provider: Apertus. Released 2025-09-01. Access: Open.

Unified ELO 1450 ± 10, rank #996 of 1776 rated models, from 292 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LatamBoard - Spanish XNLI50.76Score (%)100
LatamBoard - Spanish OpenBookQA39.4Score (%)97
LatamBoard - FLORES Bidirectional46.76Score (%)93.9
LatamBoard - Translation Score47.99Score (%)93.9
LatamBoard - Spanish COPA84.2Score (%)90.9
LatamBoard - Spanish Score63.58Score (%)90.9
EuroEval Spanish NLU - Sentiment Headlines ES49.08Sentiment classification Score (%)86.9
LatamBoard - Spanish TeleIA71.43Score (%)86.4
EuroEval Icelandic NLU - NQII55.44Reading comprehension Score (%)85.4
EuroEval Croatian NLU - MMS HR42.47Sentiment classification Score (%)83.9
EuroEval Lithuanian NLU - Atsiliepimai46.8Sentiment classification Score (%)83.6
EuroEval Faroese NLU - FoQA73.38Reading comprehension Score (%)82.7

Interactive version: theaggregate.ai/model?slug=apertus-8b-instruct-2509 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.