OpenAI GPT-4.1 vs OpenAI GPT-5.2 Pro

Detailed comparison for LLMs

OpenAIOpenAI

On Guardion's LLM vulnerability Benchmark, OpenAI GPT-5.2 Pro is the more secure of the two: GPT-4.1 scores 34.9% and GPT-5.2 Pro scores 3.8% 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

GPT-5.2 Pro is the overall winner in this comparison!

Attack Success Rate (lower is safer)

ASR for OpenAI GPT-4.1 vs OpenAI GPT-5.2 Pro. Green marks the safer model on each metric. Only the overall score is available for estimated models.

Overall (ASR)

GPT-4.1
34.9%
GPT-5.2 Pro
3.8%

TAP Attack Method (ASR)

GPT-4.1
57.6%
GPT-5.2 Pro
100.0%

Crescendo Attack Method (ASR)

GPT-4.1
44.9%
GPT-5.2 Pro
100.0%

Zero-Shot (ASR)

GPT-4.1
2.3%
GPT-5.2 Pro
100.0%

Key Highlights

  • OpenAI GPT-5.2 Pro has a lower Overall (ASR).
  • OpenAI GPT-4.1 has a lower TAP Attack Method (ASR).
  • OpenAI GPT-4.1 has a lower Crescendo Attack Method (ASR).
  • OpenAI GPT-4.1 has a lower Zero-Shot (ASR).

Security Profile

Outward is better on every axis.

OverallTAPCrescendoZero-Shot
GPT-4.1
GPT-5.2 Pro
Full security profile
OpenAI GPT-4.1
Full security profile
OpenAI GPT-5.2 Pro

Frequently asked questions

Is OpenAI GPT-4.1 or OpenAI GPT-5.2 Pro more secure?

On Guardion's LLM vulnerability Benchmark, OpenAI GPT-5.2 Pro is the more secure of the two: GPT-4.1 scores 34.9% and GPT-5.2 Pro scores 3.8% 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 GPT-4.1 vs GPT-5.2 Pro?

GPT-4.1 has a 34.9% ASR and GPT-5.2 Pro has a 3.8% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.

How were GPT-4.1 and GPT-5.2 Pro 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