Claude 4.6 Opus vs.Gemini 3 Flash (Tools)
Passed:
Claude 4.6 Opus 70.7% (58/82)
Gemini 3 Flash (Tools) 82.9% (68/82)
Average request time:
Claude 4.6 Opus 12.68s
Gemini 3 Flash (Tools) 68.14s
Passed:
Claude 4.6 Opus 70.7% (58/82)
Gemini 3 Flash (Tools) 82.9% (68/82)
Average request time:
Claude 4.6 Opus 12.68s
Gemini 3 Flash (Tools) 68.14s
Summary
Annotation Understanding
Claude 4.6 Opus
0 / 2
Gemini 3 Flash (Tools)
0 / 2
CAPTCHA
Claude 4.6 Opus
2 / 2
Gemini 3 Flash (Tools)
2 / 2
Color Identification
Claude 4.6 Opus
0 / 1
Gemini 3 Flash (Tools)
0 / 1
Defect Detection
Claude 4.6 Opus
10 / 15
Gemini 3 Flash (Tools)
14 / 15
Document Understanding
Claude 4.6 Opus
8 / 10
Gemini 3 Flash (Tools)
9 / 10
Localization
Claude 4.6 Opus
1 / 1
Gemini 3 Flash (Tools)
1 / 1
OCR
Claude 4.6 Opus
9 / 9
Gemini 3 Flash (Tools)
9 / 9
Object Counting
Claude 4.6 Opus
3 / 11
Gemini 3 Flash (Tools)
7 / 11
Object Detection
Claude 4.6 Opus
2 / 2
Gemini 3 Flash (Tools)
2 / 2
Object Measurement
Claude 4.6 Opus
1 / 1
Gemini 3 Flash (Tools)
0 / 1
Object Understanding
Claude 4.6 Opus
8 / 11
Gemini 3 Flash (Tools)
8 / 11
Receipt Reading
Claude 4.6 Opus
1 / 1
Gemini 3 Flash (Tools)
1 / 1
Sign Understanding
Claude 4.6 Opus
2 / 2
Gemini 3 Flash (Tools)
2 / 2
Spatial Relations
Claude 4.6 Opus
11 / 17
Gemini 3 Flash (Tools)
15 / 17
Web Action Understanding
Claude 4.6 Opus
4 / 4
Gemini 3 Flash (Tools)
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!