MiniMax MiniMax M1 80K vs Deepseek Deepseek R1

Detailed comparison for LLMs

MiniMaxDeepseek

On Guardion's LLM vulnerability Benchmark, Deepseek Deepseek R1 is the more secure of the two: MiniMax M1 80K scores 43.0% and Deepseek R1 scores 42.6% 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

Deepseek R1 is the overall winner in this comparison!

Attack Success Rate (lower is safer)

ASR for MiniMax MiniMax M1 80K vs Deepseek Deepseek R1. Green marks the safer model on each metric. Only the overall score is available for estimated models.

Overall (ASR)

MiniMax M1 80K
43.0%
Deepseek R1
42.6%

TAP Attack Method (ASR)

MiniMax M1 80K
100.0%
Deepseek R1
76.9%

Crescendo Attack Method (ASR)

MiniMax M1 80K
100.0%
Deepseek R1
34.8%

Zero-Shot (ASR)

MiniMax M1 80K
100.0%
Deepseek R1
16.1%

Key Highlights

  • Deepseek Deepseek R1 has a lower Overall (ASR).
  • Deepseek Deepseek R1 has a lower TAP Attack Method (ASR).
  • Deepseek Deepseek R1 has a lower Crescendo Attack Method (ASR).
  • Deepseek Deepseek R1 has a lower Zero-Shot (ASR).

Security Profile

Outward is better on every axis.

OverallTAPCrescendoZero-Shot
MiniMax M1 80K
Deepseek R1
Full security profile
MiniMax MiniMax M1 80K
Full security profile
Deepseek Deepseek R1

Frequently asked questions

Is MiniMax MiniMax M1 80K or Deepseek Deepseek R1 more secure?

On Guardion's LLM vulnerability Benchmark, Deepseek Deepseek R1 is the more secure of the two: MiniMax M1 80K scores 43.0% and Deepseek R1 scores 42.6% 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 MiniMax M1 80K vs Deepseek R1?

MiniMax M1 80K has a 43.0% ASR and Deepseek R1 has a 42.6% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.

How were MiniMax M1 80K and Deepseek R1 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