Benchmarked by Vals Logo

Gemini 2.5 Flash is the best price-performance model suitable for large scale processing with support for multiple modalities.

Avg. Accuracy

66.29%

Latency

27.13s

Cost (In/Out)

0.3 / 2.5

Context Window

1M

Max Output Tokens

66k

Input Modality

Benchmarks

Accuracy

Rankings

CaseLaw (v2)

0.0%

23/ 58

CorpFin

0.0%

31/ 78

Finance Agent

0.0%

29/ 57

MortgageTax

0.0%

19/ 57

SAGE

0.0%

8/ 36

TaxEval (v2)

0.0%

25/ 88

AIME

0.0%

45/ 79

GPQA

0.0%

13/ 80

LiveCodeBench

0.0%

27/ 87

LegalBench

0.0%

22/ 101

MedQA

0.0%

30/ 87

MGSM

0.0%

43/ 75

MMLU Pro

0.0%

21/ 80

MMMU

0.0%

13/ 54

Terminal-Bench

0.0%

31/ 47

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.