Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Object Localization on TEA (test)
Loading...
49.13
mIoU
Human
2.902
14.9035
26.905
38.9065
Feb 5, 2026
mIoU
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
mIoU
Accuracy
Human
2026.02
49.13
-
Claude-Opus-4
2026.02
43.67
-
o3-2025
2026.02
37.03
-
GPT-5
2026.02
31.74
-
GPT-4.1
2026.02
23.96
-
Gemini-2.5-Pro
2026.02
15.87
-
Gemini-2.5-Flash
2026.02
12.42
-
llama-4-Scout
2026.02
7.75
-
GPT-4o
2026.02
4.68
-
Feedback
Search any
task
Search any
task