Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sycophancy detection on LURE Truthfulness
Loading...
10
Sycophancy Rate
Gemini 3 Flash
8.08
21.04
34
46.96
Apr 8, 2026
Sycophancy Rate
Sycophancy Rate Delta
Updated 7d ago
Evaluation Results
Method
Method
Links
Sycophancy Rate
Sycophancy Rate Delta
Gemini 3 Flash
Family=Gemini, Organiz...
2026.04
10
58
Gemini 3 Pro
Family=Gemini, Organiz...
2026.04
11
42
GPT-5.2
Family=GPT, Organizati...
2026.04
18
35
GPT-4o
Family=GPT, Organizati...
2026.04
22
12
GPT-4.1
Family=GPT, Organizati...
2026.04
26
22
DeepSeek V3
Organization=DeepSeek
2026.04
36
11
Sonnet 4.5
Family=Claude, Organiz...
2026.04
44
36
Opus 4.6
Family=Claude, Organiz...
2026.04
46
44
Llama 4 Maverick†
Family=Llama, Organiza...
2026.04
55
3
Llama 4 Scout
Family=Llama, Organiza...
2026.04
58
42
Feedback
Search any
task
Search any
task