Gemini 3 Pro (11/25)

Release Date: 11/18/2025

Vals Index

Accuracy (Vals Index)

61.81% ± 1.98

Latency (Vals Index)

210.68s

Cost/Test (Vals Index)

$0.44

Context Window

1M

Max Output Tokens

66k

Input Modality

Hyperparameter settings
Default Provider : Google

Temperature

1

Top P

Default

Top K

Default

Max Output Tokens

65,536

Reasoning Effort

high

Benchmarks

Accuracy

Rankings

0.0%

± 1.98
8/ 36

0.0%

± 1.55
7/ 25

0.0%

± 0.19
35/ 43

0.0%

± 0.95
17/ 94

0.0%

± 2.80
9/ 41

0.0%

± 2.07
4/ 48

0.0%

± 1.90
37/ 48

0.0%

± 0.91
2/ 66

0.0%

± 4.02
8/ 23

0.0%

± 3.38
9/ 46

0.0%

± 0.87
31/ 101

0.0%

± 0.38
3/ 93

0.0%

± 1.39
2/ 96

0.0%

± 11.49
5/ 50

0.0%

± 0.98
6/ 102

0.0%

± 0.37
2/ 114

0.0%

± 0.18
8/ 95

0.0%

± 0.30
2/ 94

0.0%

± 0.79
3/ 63

0.0%

± 1.90
7/ 38

0.0%

± 5.30
7/ 48
Contact us
Or send us an email at contact@vals.ai
Proprietary Benchmarks (contact us to get access)
Academic Benchmarks

Read about our methodology.