Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Diagnostic Personalization on LSD
Loading...
89.3
Recall
Gemini-3.0-Pro
23.052
40.251
57.45
74.649
Feb 3, 2026
Recall
Updated 4d ago
Evaluation Results
Method
Method
Links
Recall
Gemini-3.0-Pro
Inference Protocol=w/ CAG
2026.02
89.3
Gemini-3.0-Pro
Inference Protocol=Direct
2026.02
76.2
Qwen3-VL-8B + CoViP (Ours)
Inference Protocol=w/ CAG
2026.02
58.2
Gemini-2.0-Flash
Inference Protocol=Direct
2026.02
52.7
Qwen3-VL-8B + RePIC
Inference Protocol=w/ CAG
2026.02
52.1
Qwen3-VL-8B
Inference Protocol=w/ CAG
2026.02
48.8
Gemini-2.0-Flash
Inference Protocol=w/ CAG
2026.02
46
Qwen3-VL-30B-A3B
Inference Protocol=w/ CAG
2026.02
42.1
Qwen3-VL-8B + CoViP (Ours)
Inference Protocol=Direct
2026.02
37.2
GPT-5
Inference Protocol=w/ CAG
2026.02
34.4
GPT-4o
Inference Protocol=w/ CAG
2026.02
33.6
Qwen3-VL-8B + RePIC
Inference Protocol=Direct
2026.02
32.7
Qwen3-VL-8B
Inference Protocol=Direct
2026.02
29.8
Qwen3-VL-8B + RAP
Inference Protocol=w/ CAG
2026.02
28.8
GPT-4o
Inference Protocol=Direct
2026.02
28.7
GPT-5
Inference Protocol=Direct
2026.02
28.5
Qwen3-VL-8B + RAP
Inference Protocol=Direct
2026.02
27
Qwen3-VL-30B-A3B
Inference Protocol=Direct
2026.02
25.6
Feedback
Search any
task
Search any
task