Gemini 2.0 Flash vs.Claude 4 Sonnet
Passed:
Gemini 2.0 Flash 65.1% (54/83)
Claude 4 Sonnet 71.1% (59/83)
Average request time:
Gemini 2.0 Flash 12.05s
Claude 4 Sonnet 19.72s
Passed:
Gemini 2.0 Flash 65.1% (54/83)
Claude 4 Sonnet 71.1% (59/83)
Average request time:
Gemini 2.0 Flash 12.05s
Claude 4 Sonnet 19.72s
Summary
Annotation Understanding
Gemini 2.0 Flash
2 / 2
Claude 4 Sonnet
2 / 2
CAPTCHA
Gemini 2.0 Flash
2 / 2
Claude 4 Sonnet
2 / 2
Color Identification
Gemini 2.0 Flash
0 / 1
Claude 4 Sonnet
0 / 1
Counting nodes
Gemini 2.0 Flash
0 / 1
Claude 4 Sonnet
0 / 1
Defect Detection
Gemini 2.0 Flash
9 / 15
Claude 4 Sonnet
12 / 15
Document Understanding
Gemini 2.0 Flash
9 / 10
Claude 4 Sonnet
9 / 10
Localization
Gemini 2.0 Flash
1 / 1
Claude 4 Sonnet
0 / 1
OCR
Gemini 2.0 Flash
7 / 9
Claude 4 Sonnet
7 / 9
Object Counting
Gemini 2.0 Flash
2 / 10
Claude 4 Sonnet
2 / 10
Object Detection
Gemini 2.0 Flash
1 / 2
Claude 4 Sonnet
2 / 2
Object Measurement
Gemini 2.0 Flash
0 / 2
Claude 4 Sonnet
1 / 2
Object Understanding
Gemini 2.0 Flash
7 / 11
Claude 4 Sonnet
8 / 11
Receipt Reading
Gemini 2.0 Flash
1 / 1
Claude 4 Sonnet
1 / 1
Sign Understanding
Gemini 2.0 Flash
2 / 2
Claude 4 Sonnet
2 / 2
Spatial Relations
Gemini 2.0 Flash
11 / 17
Claude 4 Sonnet
10 / 17
Web Action Understanding
Gemini 2.0 Flash
4 / 4
Claude 4 Sonnet
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!