Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Hallucination Evaluation on EventHallusion binary QA (test)
Loading...
0.655
Accuracy
SmartSight
0.52604
0.55952
0.593
0.62648
Dec 21, 2025
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
SmartSight
Base Model=Video-R1
2025.12
0.655
VCD
Base Model=Video-R1
2025.12
0.654
TCD
Base Model=Video-R1
2025.12
0.649
SmartSight
Base Model=Qwen2.5-VL-7B
2025.12
0.631
Video-R1
Decoding Method=Greedy
2025.12
0.626
DINO-HEAL
Base Model=Video-R1
2025.12
0.626
VCD
Base Model=Qwen2.5-VL-7B
2025.12
0.619
TCD
Base Model=Qwen2.5-VL-7B
2025.12
0.614
Qwen2.5-VL-7B
Decoding Method=Greedy
2025.12
0.604
DINO-HEAL
Base Model=Qwen2.5-VL-7B
2025.12
0.568
SmartSight
Base Model=LLaVA-NEXT-...
2025.12
0.558
TCD
Base Model=LLaVA-NEXT-...
2025.12
0.557
DINO-HEAL
Base Model=LLaVA-NEXT-...
2025.12
0.539
LLaVA-NEXT-Video-7B
Decoding Method=Greedy
2025.12
0.534
VCD
Base Model=LLaVA-NEXT-...
2025.12
0.531
Feedback
Search any
task
Search any
task