GPT-5 Nano vs.Qwen 3.5 122B (A10B)
Passed:
GPT-5 Nano 61.0% (50/82)
Qwen 3.5 122B (A10B) 78.0% (64/82)
Average request time:
GPT-5 Nano 13.09s
Qwen 3.5 122B (A10B) 1.54s
Passed:
GPT-5 Nano 61.0% (50/82)
Qwen 3.5 122B (A10B) 78.0% (64/82)
Average request time:
GPT-5 Nano 13.09s
Qwen 3.5 122B (A10B) 1.54s
Summary
Annotation Understanding
GPT-5 Nano
0 / 2
Qwen 3.5 122B (A10B)
1 / 2
CAPTCHA
GPT-5 Nano
0 / 2
Qwen 3.5 122B (A10B)
2 / 2
Color Identification
GPT-5 Nano
1 / 1
Qwen 3.5 122B (A10B)
1 / 1
Defect Detection
GPT-5 Nano
11 / 15
Qwen 3.5 122B (A10B)
13 / 15
Document Understanding
GPT-5 Nano
8 / 10
Qwen 3.5 122B (A10B)
9 / 10
Localization
GPT-5 Nano
0 / 1
Qwen 3.5 122B (A10B)
1 / 1
OCR
GPT-5 Nano
6 / 9
Qwen 3.5 122B (A10B)
7 / 9
Object Counting
GPT-5 Nano
1 / 11
Qwen 3.5 122B (A10B)
5 / 11
Object Detection
GPT-5 Nano
1 / 2
Qwen 3.5 122B (A10B)
2 / 2
Object Measurement
GPT-5 Nano
0 / 1
Qwen 3.5 122B (A10B)
1 / 1
Object Understanding
GPT-5 Nano
7 / 11
Qwen 3.5 122B (A10B)
8 / 11
Receipt Reading
GPT-5 Nano
1 / 1
Qwen 3.5 122B (A10B)
1 / 1
Sign Understanding
GPT-5 Nano
2 / 2
Qwen 3.5 122B (A10B)
2 / 2
Spatial Relations
GPT-5 Nano
12 / 17
Qwen 3.5 122B (A10B)
14 / 17
Web Action Understanding
GPT-5 Nano
4 / 4
Qwen 3.5 122B (A10B)
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!