Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Diagnosis on DiagnosisArena
Loading...
36.36
Top-1 Accuracy
Mixed-Vendor MAC
18.7112
23.2931
27.875
32.4569
Feb 14, 2026
Top-1 Accuracy
Top-5 Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Top-1 Accuracy
Top-5 Accuracy
Mixed-Vendor MAC
Composition=Mixed (Ope...
2026.02
36.36
49.09
Single-Vendor MAC
Model=o4-mini (OpenAI)
2026.02
35.76
47.88
Single-Vendor MAC
Model=Gemini-2.5-Pro
2026.02
33.94
44.24
Single-Vendor MAC
Model=Claude-4.5-Sonnet
2026.02
32.73
45.45
Single-LLM
Model=o4-mini (OpenAI)
2026.02
32.12
46.06
Single-LLM
Model=Gemini-2.5-Pro
2026.02
20
31.51
Single-LLM
Model=Claude-4.5-Sonnet
2026.02
19.39
29.7
Feedback
Search any
task
Search any
task