Gemini 2.0 Flash Lite vs.Qwen 2.5 VL 7B
Passed:
Gemini 2.0 Flash Lite 64.6% (53/82)
Qwen 2.5 VL 7B 56.1% (46/82)
Average request time:
Gemini 2.0 Flash Lite 8.92s
Qwen 2.5 VL 7B 10.18s
Passed:
Gemini 2.0 Flash Lite 64.6% (53/82)
Qwen 2.5 VL 7B 56.1% (46/82)
Average request time:
Gemini 2.0 Flash Lite 8.92s
Qwen 2.5 VL 7B 10.18s
Summary
Annotation Understanding
Gemini 2.0 Flash Lite
1 / 2
Qwen 2.5 VL 7B
2 / 2
CAPTCHA
Gemini 2.0 Flash Lite
0 / 2
Qwen 2.5 VL 7B
2 / 2
Color Identification
Gemini 2.0 Flash Lite
1 / 1
Qwen 2.5 VL 7B
1 / 1
Counting nodes
Gemini 2.0 Flash Lite
0 / 1
Qwen 2.5 VL 7B
0 / 1
Defect Detection
Gemini 2.0 Flash Lite
10 / 15
Qwen 2.5 VL 7B
10 / 15
Document Understanding
Gemini 2.0 Flash Lite
5 / 10
Qwen 2.5 VL 7B
5 / 10
Localization
Gemini 2.0 Flash Lite
1 / 1
Qwen 2.5 VL 7B
0 / 1
OCR
Gemini 2.0 Flash Lite
8 / 9
Qwen 2.5 VL 7B
7 / 9
Object Counting
Gemini 2.0 Flash Lite
3 / 10
Qwen 2.5 VL 7B
1 / 10
Object Detection
Gemini 2.0 Flash Lite
1 / 2
Qwen 2.5 VL 7B
1 / 2
Object Measurement
Gemini 2.0 Flash Lite
0 / 2
Qwen 2.5 VL 7B
0 / 2
Object Understanding
Gemini 2.0 Flash Lite
8 / 10
Qwen 2.5 VL 7B
7 / 10
Receipt Reading
Gemini 2.0 Flash Lite
1 / 1
Qwen 2.5 VL 7B
1 / 1
Sign Understanding
Gemini 2.0 Flash Lite
2 / 2
Qwen 2.5 VL 7B
2 / 2
Spatial Relations
Gemini 2.0 Flash Lite
13 / 17
Qwen 2.5 VL 7B
10 / 17
Web Action Understanding
Gemini 2.0 Flash Lite
4 / 4
Qwen 2.5 VL 7B
3 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!