GLM-5.3

Z.ai·glm-5-3

Rank · overall#45

Score70.0

Benchmark scores

5 benchmarks

SWE-bench Verified95.4%

% Resolved · 2026-08-14

Chatbot Arena (Coding)1560Coding Elo

Artificial Analysis48.6Intelligence Index

Arena Agent3.8%

Net Improvement · ± 0.71

FrontierMath (Tier 4)29.3%

Accuracy · ± 7.2

0 agents

This model appears only in model-level benchmarks — no harness ran it directly.

Scraped and aggregated from public leaderboards · 2026-09-07