Gemma 4 26B (A4B) vs.Qwen 3.5 9B
Passed:
Gemma 4 26B (A4B) 62.2% (51/82)
Qwen 3.5 9B 67.1% (55/82)
Average request time:
Gemma 4 26B (A4B) 8.84s
Qwen 3.5 9B 7.99s
Passed:
Gemma 4 26B (A4B) 62.2% (51/82)
Qwen 3.5 9B 67.1% (55/82)
Average request time:
Gemma 4 26B (A4B) 8.84s
Qwen 3.5 9B 7.99s
Summary
Annotation Understanding
Gemma 4 26B (A4B)
1 / 2
Qwen 3.5 9B
0 / 2
CAPTCHA
Gemma 4 26B (A4B)
2 / 2
Qwen 3.5 9B
2 / 2
Color Identification
Gemma 4 26B (A4B)
1 / 1
Qwen 3.5 9B
1 / 1
Defect Detection
Gemma 4 26B (A4B)
8 / 15
Qwen 3.5 9B
10 / 15
Document Understanding
Gemma 4 26B (A4B)
7 / 10
Qwen 3.5 9B
5 / 10
Localization
Gemma 4 26B (A4B)
1 / 1
Qwen 3.5 9B
0 / 1
OCR
Gemma 4 26B (A4B)
8 / 9
Qwen 3.5 9B
6 / 9
Object Counting
Gemma 4 26B (A4B)
2 / 11
Qwen 3.5 9B
4 / 11
Object Detection
Gemma 4 26B (A4B)
1 / 2
Qwen 3.5 9B
2 / 2
Object Measurement
Gemma 4 26B (A4B)
0 / 1
Qwen 3.5 9B
0 / 1
Object Understanding
Gemma 4 26B (A4B)
7 / 11
Qwen 3.5 9B
9 / 11
Receipt Reading
Gemma 4 26B (A4B)
1 / 1
Qwen 3.5 9B
1 / 1
Sign Understanding
Gemma 4 26B (A4B)
1 / 2
Qwen 3.5 9B
2 / 2
Spatial Relations
Gemma 4 26B (A4B)
11 / 17
Qwen 3.5 9B
16 / 17
Web Action Understanding
Gemma 4 26B (A4B)
4 / 4
Qwen 3.5 9B
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!