Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Certified Task-solving on PHACT Safety Suite (Impossible goals)
Loading...
1
False Certifications (Bare)
Llama 3.3
0.96
1.23
1.5
1.77
Jun 29, 2026
False Certifications (Bare)
False Certifications (Structured)
Updated 26d ago
Evaluation Results
Method
Method
Links
False Certifications (Bare)
False Certifications (Structured)
Llama 3.3
Model Family=Llama 3.3...
2026.06
1
0
Gemini 2.5
Model Family=Gemini 2....
2026.06
2
0
Feedback
Search any
task
Search any
task
