Meta LlamaGuard vs Meta Prompt Guard 2 86M

Detailed comparison for runtime guardrails

MetaMeta

On Guardion's Prompt Attack Risk Benchmark, Meta Prompt Guard 2 86M is the more secure of the two: LlamaGuard scores NaN% and Prompt Guard 2 86M scores NaN% on F1 score (higher is better).

Head-to-Head Overview

Prompt Guard 2 86M is the overall winner in this comparison!

Guardrail Metrics

F1 Score

LlamaGuard
0.000
Prompt Guard 2 86M
0.000

Accuracy

LlamaGuard
0.000
Prompt Guard 2 86M
0.000

Precision

LlamaGuard
0.000
Prompt Guard 2 86M
0.000

Recall

LlamaGuard
0.000
Prompt Guard 2 86M
0.000

False Positive Rate

LlamaGuard
0.000
Prompt Guard 2 86M
0.000

False Negative Rate

LlamaGuard
0.000
Prompt Guard 2 86M
0.000

Average Latency (ms)

LlamaGuard
0.000
Prompt Guard 2 86M
0.000

p50 Latency (ms)

LlamaGuard
0.000
Prompt Guard 2 86M
0.000

p90 Latency (ms)

LlamaGuard
0.000
Prompt Guard 2 86M
0.000

Key Highlights

No specific highlights generated for this comparison.

Security Profile

Outward is better on every axis.

F1 ScoreAccuracyPrecisionRecallFPRFNRAverage Latency (ms)p50 Latency (ms)p90 Latency (ms)
LlamaGuard
Prompt Guard 2 86M
Full security profile
Meta LlamaGuard
Full security profile
Meta Prompt Guard 2 86M

Frequently asked questions

Is Meta LlamaGuard or Meta Prompt Guard 2 86M more secure?

On Guardion's Prompt Attack Risk Benchmark, Meta Prompt Guard 2 86M is the more secure of the two: LlamaGuard scores NaN% and Prompt Guard 2 86M scores NaN% on F1 score (higher is better).

What is the F1 score of LlamaGuard vs Prompt Guard 2 86M?

LlamaGuard scores NaN% F1 and Prompt Guard 2 86M scores NaN% F1 on Guardion's prompt-attack benchmark. F1 balances precision and recall — higher is better.

How were LlamaGuard and Prompt Guard 2 86M tested?

Both were evaluated via API at production-like sensitivity against 30+ prompt-attack categories using zero-shot, Crescendo, and TAP methods, scored by F1.

Related Comparisons