GPT-5 (high reasoning) vs.Qwen 2.5 VL 7B
Passed:
GPT-5 (high reasoning) 73.5% (61/83)
Qwen 2.5 VL 7B 55.6% (45/81)
Average request time:
GPT-5 (high reasoning) 26.96s
Qwen 2.5 VL 7B 45.63s
Passed:
GPT-5 (high reasoning) 73.5% (61/83)
Qwen 2.5 VL 7B 55.6% (45/81)
Average request time:
GPT-5 (high reasoning) 26.96s
Qwen 2.5 VL 7B 45.63s
Summary
Annotation Understanding
GPT-5 (high reasoning)
1 / 2
Qwen 2.5 VL 7B
1 / 2
CAPTCHA
GPT-5 (high reasoning)
0 / 2
Qwen 2.5 VL 7B
2 / 2
Color Identification
GPT-5 (high reasoning)
1 / 1
Qwen 2.5 VL 7B
0 / 1
Counting nodes
GPT-5 (high reasoning)
0 / 1
Qwen 2.5 VL 7B
0 / 0
Defect Detection
GPT-5 (high reasoning)
12 / 15
Qwen 2.5 VL 7B
9 / 15
Document Understanding
GPT-5 (high reasoning)
8 / 10
Qwen 2.5 VL 7B
8 / 10
Localization
GPT-5 (high reasoning)
1 / 1
Qwen 2.5 VL 7B
1 / 1
OCR
GPT-5 (high reasoning)
9 / 9
Qwen 2.5 VL 7B
6 / 9
Object Counting
GPT-5 (high reasoning)
3 / 10
Qwen 2.5 VL 7B
1 / 9
Object Detection
GPT-5 (high reasoning)
1 / 2
Qwen 2.5 VL 7B
1 / 2
Object Measurement
GPT-5 (high reasoning)
0 / 2
Qwen 2.5 VL 7B
0 / 2
Object Understanding
GPT-5 (high reasoning)
9 / 11
Qwen 2.5 VL 7B
5 / 11
Receipt Reading
GPT-5 (high reasoning)
1 / 1
Qwen 2.5 VL 7B
0 / 1
Sign Understanding
GPT-5 (high reasoning)
2 / 2
Qwen 2.5 VL 7B
2 / 2
Spatial Relations
GPT-5 (high reasoning)
15 / 17
Qwen 2.5 VL 7B
11 / 17
Web Action Understanding
GPT-5 (high reasoning)
4 / 4
Qwen 2.5 VL 7B
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!