Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Artifact Localization on LOKI (test)
Loading...
0.175
mIoU
DiffDoctor
0.0086
0.0518
0.095
0.1382
Feb 24, 2026
mIoU
F1
Updated 4d ago
Evaluation Results
Method
Method
Links
mIoU
F1
DiffDoctor
Method Type=Artifact S...
2026.02
0.175
0.274
Qwen2.5-VL-7B + ArtiAgent
Mode=Fine-tuned with A...
2026.02
0.129
0.198
InternVL3.5-8B + ArtiAgent
Mode=Fine-tuned with A...
2026.02
0.126
0.196
Gemini-2.5-Pro
System Category=Propri...
2026.02
0.109
0.169
LEGION
Method Type=Artifact S...
2026.02
0.1
0.158
GPT-5
System Category=Propri...
2026.02
0.089
0.141
Qwen2.5-VL-7B
Mode=Vanilla
2026.02
0.052
0.068
GPT-4o
System Category=Propri...
2026.02
0.037
0.056
PAL
Method Type=Artifact S...
2026.02
0.021
0.037
InternVL3.5-8B
Mode=Vanilla
2026.02
0.015
0.025
Feedback
Search any
task
Search any
task