Mistral Medium 3 vs.Cosmos Reason2 2B
Passed:
Mistral Medium 3 68.7% (57/83)
Cosmos Reason2 2B 41.5% (34/82)
Average request time:
Mistral Medium 3 13.13s
Cosmos Reason2 2B 1.94s
Passed:
Mistral Medium 3 68.7% (57/83)
Cosmos Reason2 2B 41.5% (34/82)
Average request time:
Mistral Medium 3 13.13s
Cosmos Reason2 2B 1.94s
Summary
Annotation Understanding
Mistral Medium 3
1 / 2
Cosmos Reason2 2B
0 / 2
CAPTCHA
Mistral Medium 3
2 / 2
Cosmos Reason2 2B
2 / 2
Color Identification
Mistral Medium 3
0 / 1
Cosmos Reason2 2B
1 / 1
Defect Detection
Mistral Medium 3
12 / 15
Cosmos Reason2 2B
9 / 15
Document Understanding
Mistral Medium 3
8 / 10
Cosmos Reason2 2B
4 / 10
Localization
Mistral Medium 3
1 / 1
Cosmos Reason2 2B
0 / 1
OCR
Mistral Medium 3
9 / 9
Cosmos Reason2 2B
6 / 9
Object Counting
Mistral Medium 3
2 / 11
Cosmos Reason2 2B
1 / 11
Object Detection
Mistral Medium 3
2 / 2
Cosmos Reason2 2B
1 / 2
Object Measurement
Mistral Medium 3
0 / 1
Cosmos Reason2 2B
0 / 1
Object Understanding
Mistral Medium 3
9 / 11
Cosmos Reason2 2B
6 / 11
Receipt Reading
Mistral Medium 3
1 / 1
Cosmos Reason2 2B
1 / 1
Sign Understanding
Mistral Medium 3
2 / 2
Cosmos Reason2 2B
2 / 2
Spatial Relations
Mistral Medium 3
7 / 17
Cosmos Reason2 2B
4 / 17
Web Action Understanding
Mistral Medium 3
4 / 4
Cosmos Reason2 2B
0 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!