Mistral Medium 3 vs.SmolVLM2 2.2B
Passed:
Mistral Medium 3 68.7% (57/83)
SmolVLM2 2.2B 36.6% (30/82)
Average request time:
Mistral Medium 3 13.13s
SmolVLM2 2.2B 4.16s
Passed:
Mistral Medium 3 68.7% (57/83)
SmolVLM2 2.2B 36.6% (30/82)
Average request time:
Mistral Medium 3 13.13s
SmolVLM2 2.2B 4.16s
Summary
Annotation Understanding
Mistral Medium 3
1 / 2
SmolVLM2 2.2B
2 / 2
CAPTCHA
Mistral Medium 3
2 / 2
SmolVLM2 2.2B
0 / 2
Color Identification
Mistral Medium 3
0 / 1
SmolVLM2 2.2B
0 / 1
Defect Detection
Mistral Medium 3
12 / 15
SmolVLM2 2.2B
9 / 15
Document Understanding
Mistral Medium 3
8 / 10
SmolVLM2 2.2B
3 / 10
Localization
Mistral Medium 3
1 / 1
SmolVLM2 2.2B
0 / 1
OCR
Mistral Medium 3
9 / 9
SmolVLM2 2.2B
2 / 9
Object Counting
Mistral Medium 3
2 / 11
SmolVLM2 2.2B
1 / 11
Object Detection
Mistral Medium 3
2 / 2
SmolVLM2 2.2B
1 / 2
Object Measurement
Mistral Medium 3
0 / 1
SmolVLM2 2.2B
0 / 1
Object Understanding
Mistral Medium 3
9 / 11
SmolVLM2 2.2B
3 / 11
Receipt Reading
Mistral Medium 3
1 / 1
SmolVLM2 2.2B
0 / 1
Sign Understanding
Mistral Medium 3
2 / 2
SmolVLM2 2.2B
2 / 2
Spatial Relations
Mistral Medium 3
7 / 17
SmolVLM2 2.2B
10 / 17
Web Action Understanding
Mistral Medium 3
4 / 4
SmolVLM2 2.2B
0 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!