Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Factuality and Hallucination Detection on LongFact Objects
Loading...
99.2
Factuality Score
GPT-5.2 High
-3.0632
23.4859
50.035
76.5841
Jun 30, 2026
Factuality Score
FactScore
Updated 23d ago
Evaluation Results
Method
Method
Links
Factuality Score
FactScore
GPT-5.2 High
2026.06
99.2
-
Claude-Opus-4.5
2026.06
99
-
Claude-Sonnet-4.5
2026.06
98.8
-
Gemini-3-pro High
2026.06
98.1
-
Seed2.0 Pro
2026.06
92.9
-
GPT-5-mini
Tier=High
2026.06
0.992
-
Gemini-3-Flash
Tier=High
2026.06
0.979
-
Seed2.0 Lite
2026.06
0.922
-
Seed2.0 Mini
2026.06
0.87
-
Feedback
Search any
task
Search any
task