Models

Release date

Models

Gemini 3 Flash (12/25)

Release Date: 12/17/2025

Benchmarked by Vals Logo

Google's newest budget workhorse model

Avg. Accuracy

68.48%

Latency

306.42s

Cost (In/Out)

0.5 / 3

Context Window

1M

Max Output Tokens

66k

Input Modality

Benchmarks

Accuracy

Rankings

0.0%

8/ 31

0.0%

8/ 31

Vals Multimodal Index

0.0%

4/ 19

0.0%

4/ 19

0.0%

33/ 58

0.0%

33/ 58

0.0%

3/ 78

0.0%

3/ 78

0.0%

23/ 57

0.0%

23/ 57

0.0%

3/ 57

0.0%

3/ 57

0.0%

5/ 13

0.0%

5/ 13

0.0%

2/ 36

0.0%

2/ 36

0.0%

16/ 88

0.0%

16/ 88

0.0%

3/ 79

0.0%

3/ 79

0.0%

4/ 80

0.0%

4/ 80

0.0%

2/ 41

0.0%

2/ 41

0.0%

4/ 87

0.0%

4/ 87

0.0%

2/ 101

0.0%

2/ 101

0.0%

9/ 87

0.0%

9/ 87

0.0%

10/ 75

0.0%

10/ 75

0.0%

2/ 80

0.0%

2/ 80

0.0%

1/ 54

0.0%

1/ 54

0.0%

1/ 46

0.0%

1/ 46

0.0%

3/ 47

0.0%

3/ 47

Terminal-Bench 2.0

0.0%

4/ 31

0.0%

4/ 31

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Join our mailing list to receive benchmark updates

Model benchmarks are seriously lacking. With Vals AI, we report how language models perform on the industry-specific tasks where they will be used.

By subscribing, I agree to Vals' Privacy Policy.