Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Hallucination Mitigation on VRIPT-HAL
Loading...
52.1
F1 Score
VideoChat-R1
23.5
30.925
38.35
45.775
Dec 21, 2025
F1 Score
Hallucination Gain
Updated 3d ago
Evaluation Results
Method
Method
Links
F1 Score
Hallucination Gain
VideoChat-R1
Mitigation Method=Smar...
2025.12
52.1
3.7
Qwen2.5-VL-7B
Mitigation Method=Smar...
2025.12
50
2.1
Gemini 1.5 Pro
Mitigation Method=Base...
2025.12
49.3
-
VideoChat-R1
Mitigation Method=Base...
2025.12
48.4
-
Qwen2.5-VL-7B
Mitigation Method=Base...
2025.12
47.9
-
Claude 3.5 Sonnet
Mitigation Method=Base...
2025.12
44.6
-
InternVL3-8B
Mitigation Method=Smar...
2025.12
34.1
3.7
LLaVA-OneVision-7B
Mitigation Method=Smar...
2025.12
31.4
5.6
InternVL3-8B
Mitigation Method=Base...
2025.12
30.4
-
LLaVA-OneVision-7B
Mitigation Method=Base...
2025.12
25.8
-
Video-LLaVA
Mitigation Method=Smar...
2025.12
25.7
1.1
Video-LLaVA
Mitigation Method=Base...
2025.12
24.6
-
Feedback
Search any
task
Search any
task