Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
OCR-based Visual Question Answering on OCRVQA
Loading...
63.2
Mean Accuracy
Qwen3-VL-8B-Instruct
-2.528
14.536
31.6
48.664
Oct 3, 2025
Oct 26, 2025
Nov 18, 2025
Dec 11, 2025
Jan 3, 2026
Jan 26, 2026
Feb 18, 2026
Mean Accuracy
Updated 2d ago
Evaluation Results
Method
Method
Links
Mean Accuracy
Qwen3-VL-8B-Instruct
Strategy=Instruct
2026.02
63.2
SAP
Strategy=SAP
2026.02
62.8
Qwen3-VL-8B-Thinking
Strategy=LongCoT
2026.02
44.1
(2)
Adaptation strategy=Mo...
2025.10
13.8
TTAug
Adaptation strategy=Te...
2025.10
12.6
(1)
Adaptation strategy=(1)
2025.10
11.9
TTAug
test-time scaling=Meth...
2025.10
11.8
Method ④
test-time scaling=Othe...
2025.10
0.2
Baseline
test-time scaling=none
2025.10
0
Method ①
test-time scaling=Othe...
2025.10
0
Method ②
test-time scaling=Othe...
2025.10
0
Method ③
test-time scaling=Othe...
2025.10
0
Baseline
2025.10
0
Feedback
Search any
task
Search any
task