---
title: "GLM 5 744B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for GLM 5."
source: "https://rankedagi.com/models/glm-5-744b"
---

# GLM 5

| Field | Value |
| --- | --- |
| Organization | Z.ai |
| License | Proprietary |
| Type | Thinking |
| Size | 744B |
| Version | Latest |
| Released | 2026-02-12 |
| Last updated | 2026-05-04T03:43:08.354Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 72.6% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 48.7% | Diverse Agentic Coding |  |
| SWEBench Verified | coding | 77.8% | Agentic Coding | https://www.swebench.com/index.html |
| Terminal-Bench 2.0 | coding | 56.2% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| RankedAGI Agentic | Agents | 64.5% | RankedAGI Agentic Score |  |
| Code Arena | coding | 1436 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| Livebench Coding 26.1 | coding | 73.6% | Livebench Coding 26.01.08 | https://livebench.ai/#/?Coding=a&sort=Coding+Average&variants=true&highunseenbias=true |
| LiveBench Agentic Coding 26.1 | coding | 55.0% |  | https://livebench.ai/#/?Agentic+Coding=a&sort=Agentic+Coding+Average&variants=true&highunseenbias=true |
| SvelteBench | coding | 88.9% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| CyberGym | safety | 43.2% |  |  |
| RankedAGI Reasoning | reasoning | 70.3% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 30.5% | Multidisciplinary Reasoning (no tools) |  |
| Humanity's Last Exam w/ Tools | reasoning | 50.4% | Multidisciplinary Reasoning (with tools) |  |
| GPQA Diamond | reasoning | 86.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1456 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2026 | math | 92.7% | AIME 2026 Competition Math | https://matharena.ai/?comp=aime--aime_2026&view=problem |
| Vending Bench 2 | Agents | $4,432.12 | Benchmark for measuring AI model performance on running a business over long time horizons. Models are tasked with running a simulated vending machine business over a year and scored on their bank account balance at the end. | https://andonlabs.com/evals/vending-bench-2 |
| NYT Connections Extended | reasoning | 81.7% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| RankedAGI Math | math | 76.0% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 64.1% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 1404 | Office Tasks (Artificial Analysis) |  |
| Code DesignArena | Design | 1314 |  | https://www.designarena.ai/leaderboard/code |
| Toolathlon | Agents | 39.2% | Benchmark to assess language agents' general tool use in realistic environments. | https://toolathlon.xyz/introduction |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://z.ai/blog/glm-5 |