OpenAI o3-mini vs Zhipu AI GLM-4.5V

Detailed comparison for LLMs

OpenAIZhipu AI

On Guardion's LLM vulnerability Benchmark, OpenAI o3-mini is the more secure of the two: o3-mini scores 9.0% and GLM-4.5V scores 43.0% on attack success rate (ASR) (lower is better). One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.

Head-to-Head Overview

o3-mini is the overall winner in this comparison!

Attack Success Rate (lower is safer)

ASR for OpenAI o3-mini vs Zhipu AI GLM-4.5V. Green marks the safer model on each metric. Only the overall score is available for estimated models.

Overall (ASR)

o3-mini
9.0%
GLM-4.5V
43.0%

TAP Attack Method (ASR)

o3-mini
100.0%
GLM-4.5V
100.0%

Crescendo Attack Method (ASR)

o3-mini
100.0%
GLM-4.5V
100.0%

Zero-Shot (ASR)

o3-mini
100.0%
GLM-4.5V
100.0%

Key Highlights

  • OpenAI o3-mini has a lower Overall (ASR).

Security Profile

Outward is better on every axis.

OverallTAPCrescendoZero-Shot
o3-mini
GLM-4.5V
Full security profile
OpenAI o3-mini
Full security profile
Zhipu AI GLM-4.5V

Frequently asked questions

Is OpenAI o3-mini or Zhipu AI GLM-4.5V more secure?

On Guardion's LLM vulnerability Benchmark, OpenAI o3-mini is the more secure of the two: o3-mini scores 9.0% and GLM-4.5V scores 43.0% on attack success rate (ASR) (lower is better). One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.

What is the attack success rate (ASR) of o3-mini vs GLM-4.5V?

o3-mini has a 9.0% ASR and GLM-4.5V has a 43.0% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.

How were o3-mini and GLM-4.5V tested?

Both were red-teamed with the HarmBench framework across zero-shot, TAP (Tree of Attacks with Pruning), and Crescendo multi-turn attacks, scored by Attack Success Rate.

Related Comparisons