Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mirror Counting on TEA (test)
Loading...
98
Accuracy
o3-2025
82.4
86.45
90.5
94.55
Feb 5, 2026
Accuracy
mIoU
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
mIoU
o3-2025
2026.02
98
-
Claude-Opus-4
2026.02
97
-
llama-4-Scout
2026.02
97
-
GPT-4o
2026.02
92
-
GPT-5
2026.02
88
-
GPT-4.1
2026.02
88
-
Gemini-2.5-Pro
2026.02
88
-
Gemini-2.5-Flash
2026.02
87
-
Human
2026.02
83
-
Feedback
Search any
task
Search any
task