Skip to main content

LLM Leaderboard

MODEL PERFORMANCE ACROSS 24 SCANS

🥇
Claude Sonnet 4.6Anthropic
24 scans analyzed
77/100 avg
70%
POSITIVE
7%
NEGATIVE
0
RED FLAGS
0
HALLUC.
🥈
Gemini 3.1 ProGoogle
24 scans analyzed
76/100 avg
67%
POSITIVE
8%
NEGATIVE
0
RED FLAGS
0
HALLUC.
🥉
GPT-5OpenAI
24 scans analyzed
75/100 avg
65%
POSITIVE
8%
NEGATIVE
0
RED FLAGS
0
HALLUC.
GPT-5 MiniOpenAI
24 scans analyzed
72/100 avg
61%
POSITIVE
10%
NEGATIVE
0
RED FLAGS
0
HALLUC.
Gemini 3 FlashGoogle
24 scans analyzed
70/100 avg
57%
POSITIVE
12%
NEGATIVE
0
RED FLAGS
0
HALLUC.
DeepSeek V3DeepSeek
24 scans analyzed
69/100 avg
55%
POSITIVE
12%
NEGATIVE
0
RED FLAGS
0
HALLUC.
GPT-6 LunaOpenAI
0 scans analyzed
0/100 avg
0%
POSITIVE
0%
NEGATIVE
0
RED FLAGS
0
HALLUC.
GPT-6 SolOpenAI
0 scans analyzed
0/100 avg
0%
POSITIVE
0%
NEGATIVE
0
RED FLAGS
0
HALLUC.
Claude Sonnet 5Anthropic
0 scans analyzed
0/100 avg
0%
POSITIVE
0%
NEGATIVE
0
RED FLAGS
0
HALLUC.
Gemini 3.8 FlashGoogle
0 scans analyzed
0/100 avg
0%
POSITIVE
0%
NEGATIVE
0
RED FLAGS
0
HALLUC.
Claude Fable 5.1Anthropic
0 scans analyzed
0/100 avg
0%
POSITIVE
0%
NEGATIVE
0
RED FLAGS
0
HALLUC.