GLM-4.7 (Thinking) — benchmark results

Provider: Zhipu. Released 2025-12-22. Access: Open.

Unified ELO 1696 ± 36, rank #280 of 1776 rated models, from 8 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LLM2014 Logic 2025-1265.49Median Score86
BenchTable69.6Total Score (%)85.5
LLM2014 Logic 2026-0162.94Median Score84.1
ProfBench46.6Overall Rubric Score (%)60.1
LiveMedBench13.35Overall Score (%)59.5
LisanBench0.01Mean Path Length / Current Maximum36.2
SecCodeBench52.29Total Score28.6
HalluHard0.73Turn-1 Hallucination Rate19.4

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