Qwen 3 8B (Non-reasoning) — benchmark results

Qwen 3 8B evaluated with reasoning disabled. Provider: Alibaba. Released 2025-04-28. Access: Open.

Unified ELO 1534 ± 7, rank #665 of 1776 rated models, from 295 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Ukrainian Summarization - LR SUM UK31.21Score (%)93.8
EuroEval Italian Summarization - Ilpost SUM38.55Score (%)93.3
EuroEval Catalan Summarization - Dacsa CA38.65Score (%)92.2
EuroEval Spanish Summarization - Mlsum ES29.13Score (%)91.8
EuroEval Ukrainian NLU - Cross Domain UK Reviews62.26Sentiment classification Score (%)91.8
EuroEval Icelandic Summarization - RRN37.96Score (%)91.6
EuroEval Catalan NLU - MultiWikiQA CA74.17Reading comprehension Score (%)89.6
EuroEval Albanian NLU - MultiWikiQA SQ63.62Reading comprehension Score (%)89.4
EuroEval Slovene NLU - MultiWikiQA SL68.43Reading comprehension Score (%)89.2
EuroEval Polish NLU - Polemo292.97Sentiment classification Score (%)88.2
EuroEval Estonian Summarization - ERR News30.97Score (%)87.9
EuroEval Bosnian Summarization - LR SUM BS30.6Score (%)87.5

Interactive version: theaggregate.ai/model?slug=qwen-3-8b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.