Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Artifact Explanation on LOKI (test)
Loading...
0.169
ROUGE
Qwen2.5-VL-7B + ArtiAgent
0.07748
0.10124
0.125
0.14876
Feb 24, 2026
ROUGE
CSS
Updated 4d ago
Evaluation Results
Method
Method
Links
ROUGE
CSS
Qwen2.5-VL-7B + ArtiAgent
Fine-tuning=100K train...
2026.02
0.169
0.454
InternVL3.5-8B + ArtiAgent
Fine-tuning=100K train...
2026.02
0.137
0.401
LEGION
Training Split=SynthSc...
2026.02
0.133
0.314
GPT-5
2026.02
0.121
0.382
GPT-4o
2026.02
0.107
0.266
Qwen2.5-VL-7B
Fine-tuning=Vanilla
2026.02
0.106
0.267
Gemini-2.5-Pro
2026.02
0.097
0.358
InternVL3.5-8B
Fine-tuning=Vanilla
2026.02
0.081
0.189
Feedback
Search any
task
Search any
task