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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Catalan NLU - Guia CAT | 76.04 | Sentiment classification Score (%) | 98.8 |
| EuroEval Italian NLU | 66.72 | NLU Average Score (%) | 96 |
| EuroEval Polish NLU - Polemo2 | 95.48 | Sentiment classification Score (%) | 95.7 |
| EuroEval Italian NLU - ScaLA IT | 55.95 | Linguistic acceptability Score (%) | 94.7 |
| EuroEval Portuguese NLU - SST-2 PT | 85.45 | Sentiment classification Score (%) | 94.3 |
| EuroEval English NLU | 73.87 | NLU Average Score (%) | 94.2 |
| EuroEval Danish NLU - Angry Tweets | 58.48 | Sentiment classification Score (%) | 94 |
| EuroEval German NLU - GermEval | 71.44 | Named entity recognition Score (%) | 93.8 |
| EuroEval French NLU | 71.67 | NLU Average Score (%) | 92.8 |
| EuroEval Portuguese NLU - ScaLA PT | 45.41 | Linguistic acceptability Score (%) | 92.5 |
| EuroEval Portuguese NLU | 62.27 | NLU Average Score (%) | 92.4 |
| EuroEval English NLU - CoNLL EN | 84.35 | Named 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.