Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Count Reasoning on CountQA (test)
Loading...
25.03
EM
GPT-4o
6.258
11.1315
16.005
20.8785
Jun 22, 2026
EM
Updated 1mo ago
Evaluation Results
Method
Method
Links
EM
GPT-4o
Supervision=Zero-shot/...
2026.06
25.03
ABACUS-3B
Supervision=Zero-shot/...
2026.06
15.3
UniLIP-3B
Supervision=Zero-shot/...
2026.06
9.23
WS-COC-7B
Supervision=Image-leve...
2026.06
8.44
Show-o
Supervision=Zero-shot/...
2026.06
7.85
Janus Pro 7B
Supervision=Zero-shot/...
2026.06
6.98
Feedback
Search any
task
Search any
task