GLM-4.7 Flash — benchmark results

Zhipu GLM-4.7 Flash model row. Provider: Zhipu. Released 2026-01-19. Access: Open.

Unified ELO 1563 ± 8, rank #583 of 1776 rated models, from 281 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Catalan NLU - Guia CAT76.04Sentiment classification Score (%)98.8
EuroEval Italian NLU66.72NLU Average Score (%)96
EuroEval Polish NLU - Polemo295.48Sentiment classification Score (%)95.7
EuroEval Italian NLU - ScaLA IT55.95Linguistic acceptability Score (%)94.7
EuroEval Portuguese NLU - SST-2 PT85.45Sentiment classification Score (%)94.3
EuroEval English NLU73.87NLU Average Score (%)94.2
EuroEval Danish NLU - Angry Tweets58.48Sentiment classification Score (%)94
EuroEval German NLU - GermEval71.44Named entity recognition Score (%)93.8
EuroEval French NLU71.67NLU Average Score (%)92.8
EuroEval Portuguese NLU - ScaLA PT45.41Linguistic acceptability Score (%)92.5
EuroEval Portuguese NLU62.27NLU Average Score (%)92.4
EuroEval English NLU - CoNLL EN84.35Named entity recognition Score (%)92.2

Interactive version: theaggregate.ai/model?slug=glm-4-7-flash · How the rankings work · Data refreshed daily, snapshot 2026-07-22.