Model Security Scorecards

63.7%

Meta

meta-llama-4-scout

Critical Risk

Scans 25

Reports 318

Probes 432,060

Last Scan 2 months ago

Vulns 409

Risk Score 50.0%

54.4%

Meta

meta-llama-3-3

Retired

Critical Risk

Scans 25

Reports 314

Probes 433,948

Last Scan 2 months ago

Vulns 333

Risk Score 40.71%

39.6%

OpenAI

openai-gpt-4-1

Retired

High Risk

Scans 24

Reports 28

Probes 46,004

Last Scan 2 months ago

Vulns 188

Risk Score 22.98%

37.0%

Twitter / X

x-grok-3

Retired

High Risk

Scans 25

Reports 108

Probes 149,256

Last Scan 2 months ago

Vulns 52

Risk Score 6.36%

36.1%

Meta

meta-llama-4-maverick

High Risk

Scans 25

Reports 318

Probes 432,564

Last Scan 2 months ago

Vulns 359

Risk Score 43.89%

32.0%

OpenAI

openai-gpt-5-2

High Risk

Scans 25

Reports 241

Probes 336,962

Last Scan 2 months ago

Vulns 49

Risk Score 5.99%

18.9%

grok-4-20-beta

Moderate Risk

Scans 12

Reports 12

Probes 19,716

Last Scan 3 months ago

Vulns 0

Risk Score 0.0%

18.9%

grok-4-20

Moderate Risk

Scans 13

Reports 13

Probes 21,359

Last Scan 2 months ago

Vulns 0

Risk Score 0.0%

17.1%

OpenAI

openai-gpt-5-mini

Moderate Risk

Scans 25

Reports 107

Probes 147,874

Last Scan 2 months ago

Vulns 139

Risk Score 16.99%

16.6%

google-gemma-4-31b

Moderate Risk

Scans 8

Reports 19

Probes 530,854

Last Scan 2 months ago

Vulns 0

Risk Score 0.0%

13.8%

Anthropic

claude-4-5-haiku

Moderate Risk

Scans 25

Reports 347

Probes 480,547

Last Scan 2 months ago

Vulns 106

Risk Score 12.96%

13.8%

Twitter / X

x-grok-4

Moderate Risk

Scans 25

Reports 212

Probes 320,128

Last Scan 2 months ago

Vulns 280

Risk Score 34.23%

7.2%

claude-sonnet-4-6

Low Risk

Scans 13

Reports 13

Probes 21,359

Last Scan 2 months ago

Vulns 0

Risk Score 0.0%

7.0%

OpenAI

openai-o4

Retired

Low Risk

Scans 5

Reports 5

Probes 6,910

Last Scan 3 months ago

Vulns 14

Risk Score 1.71%

5.9%

Anthropic

claude-4-6-opus

Low Risk

Scans 25

Reports 225

Probes 314,343

Last Scan 2 months ago

Vulns 1

Risk Score 0.12%

4.9%

Anthropic

claude-4-5-sonnet

Low Risk

Scans 25

Reports 318

Probes 439,476

Last Scan 2 months ago

Vulns 51

Risk Score 6.23%

4.3%

OpenAI

openai-gpt-5-pro

Low Risk

Scans 25

Reports 95

Probes 131,290

Last Scan 2 months ago

Vulns 2

Risk Score 0.24%

4.2%

Anthropic

claude-4-opus

Retired

Low Risk

Scans 16

Reports 16

Probes 19,712

Last Scan 2 months ago

Vulns 14

Risk Score 1.71%

3.4%

Anthropic

claude-4-5-opus

Low Risk

Scans 25

Reports 106

Probes 146,492

Last Scan 2 months ago

Vulns 40

Risk Score 4.89%

2.9%

OpenAI

openai-gpt-5-nano

Low Risk

Scans 25

Reports 103

Probes 142,346

Last Scan 2 months ago

Vulns 111

Risk Score 13.57%

0.0%

openrouter-openai-compatible

Low Risk

Scans 16

Reports 16

Probes 16

Last Scan 2 months ago

Vulns 0

Risk Score 0.0%

0.0%

OpenAI

openai-o4-mini-high

Retired

Low Risk

Scans 16

Reports 16

Probes 32

Last Scan 2 months ago

Vulns 99

Risk Score 12.1%