Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
LLM Routing on SUPERGPQA
Loading...
77.6
Top-1 Acc
ORACLE
29.968
42.334
54.7
67.066
Jan 14, 2026
Top-1 Acc
Top-3 Acc
Updated 3d ago
Evaluation Results
Method
Method
Links
Top-1 Acc
Top-3 Acc
ORACLE
Model Pool=Pool Large,...
2026.01
77.6
-
ORACLE
Model Pool=Pool Small,...
2026.01
67.8
-
TOP-1 / TOP-3
Model Pool=Pool Large,...
2026.01
54.4
54.7
LLMRANK
Model Pool=Pool Large,...
2026.01
52.6
-
AVENGERS
Model Pool=Pool Large,...
2026.01
51.7
-
CASCAL-GT
Model Pool=Pool Large,...
2026.01
51.3
53.4
SMOOTHIE
Model Pool=Pool Large,...
2026.01
44.5
48.5
CASCAL
Model Pool=Pool Large,...
2026.01
42.9
52.3
TOP-1 / TOP-3
Model Pool=Pool Small,...
2026.01
37.3
35.7
LLMRANK
Model Pool=Pool Small,...
2026.01
36.4
-
CASCAL-GT
Model Pool=Pool Small,...
2026.01
36.3
31.4
AVENGERS
Model Pool=Pool Small,...
2026.01
36.3
-
CASCAL
Model Pool=Pool Small,...
2026.01
36.2
31.7
SMOOTHIE
Model Pool=Pool Small,...
2026.01
31.8
32.2
Feedback
Search any
task
Search any
task