Gemini 3 Pro (11/25)

Release Date: 11/18/2025

Benchmarked by Vals Logo
Vals Index

Gemini 3 Pro, Google's most powerful model.

Avg. Accuracy

71.2%

Latency

177.0s

Cost (In/Out)

2.00 / 12.00

Context Window

1M

Max Output Tokens

66k

Input Modality

Benchmarks

Accuracy

Rankings

SAGE

0.0%

26/ 26

FinanceAgent

0.0%

48/ 48

CorpFin

0.0%

62/ 62

CaseLaw

0.0%

44/ 44

TaxEval

0.0%

78/ 78

MortgageTax

0.0%

49/ 49

Math500

0.0%

54/ 54

AIME

0.0%

68/ 68

MGSM

0.0%

70/ 70

LegalBench

0.0%

93/ 93

MedQA

0.0%

74/ 74

GPQA

0.0%

70/ 70

MMLU Pro

0.0%

68/ 68

LiveCodeBench

0.0%

68/ 68

IOI

0.0%

25/ 25

Terminal-Bench

0.0%

35/ 35

SWE-bench

0.0%

31/ 31

Vals Index

0.0%

24/ 24

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.