Gemma 4 31B IT

Release Date: 4/2/2026

Vals Index

Accuracy (Vals Index)

38.94% ± 1.53

Latency (Vals Index)

323.18s

Avg. Cost (In/Out)

N/A

Context Window

262k

Max Output Tokens

33k

Input Modality

Hyperparameter settings
Default Provider : Google

Temperature

1

Top P

Default

Top K

Default

Max Output Tokens

32,768

Reasoning Effort

high

Show rankings only among open weight models

Benchmarks

Accuracy

Rankings

0.0%

± 1.53
35/ 39

0.0%

± 1.36
26/ 27

0.0%

± 1.34
37/ 46

0.0%

± 2.86
21/ 44

0.0%

± 0.97
31/ 68

0.0%

± 3.41
1/ 48

0.0%

± 5.21
23/ 51
Contact us
Or send us an email at contact@vals.ai
Proprietary Benchmarks (contact us to get access)
Academic Benchmarks

Read about our methodology.