Gemini 2.5 Pro vs.Cosmos Reason2 2B
Passed:
Gemini 2.5 Pro 74.4% (61/82)
Cosmos Reason2 2B 41.5% (34/82)
Average request time:
Gemini 2.5 Pro 9.95s
Cosmos Reason2 2B 1.94s
Passed:
Gemini 2.5 Pro 74.4% (61/82)
Cosmos Reason2 2B 41.5% (34/82)
Average request time:
Gemini 2.5 Pro 9.95s
Cosmos Reason2 2B 1.94s
Summary
Annotation Understanding
Gemini 2.5 Pro
1 / 2
Cosmos Reason2 2B
0 / 2
CAPTCHA
Gemini 2.5 Pro
2 / 2
Cosmos Reason2 2B
2 / 2
Color Identification
Gemini 2.5 Pro
0 / 1
Cosmos Reason2 2B
1 / 1
Defect Detection
Gemini 2.5 Pro
10 / 15
Cosmos Reason2 2B
9 / 15
Document Understanding
Gemini 2.5 Pro
9 / 10
Cosmos Reason2 2B
4 / 10
Localization
Gemini 2.5 Pro
1 / 1
Cosmos Reason2 2B
0 / 1
OCR
Gemini 2.5 Pro
9 / 9
Cosmos Reason2 2B
6 / 9
Object Counting
Gemini 2.5 Pro
4 / 11
Cosmos Reason2 2B
1 / 11
Object Detection
Gemini 2.5 Pro
2 / 2
Cosmos Reason2 2B
1 / 2
Object Measurement
Gemini 2.5 Pro
0 / 1
Cosmos Reason2 2B
0 / 1
Object Understanding
Gemini 2.5 Pro
8 / 11
Cosmos Reason2 2B
6 / 11
Receipt Reading
Gemini 2.5 Pro
1 / 1
Cosmos Reason2 2B
1 / 1
Sign Understanding
Gemini 2.5 Pro
2 / 2
Cosmos Reason2 2B
2 / 2
Spatial Relations
Gemini 2.5 Pro
14 / 17
Cosmos Reason2 2B
4 / 17
Web Action Understanding
Gemini 2.5 Pro
4 / 4
Cosmos Reason2 2B
0 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!