MiniMax-M2.5

Release Date: 2/12/2026

Benchmarked by Vals Logo
Vals Index

Avg. Accuracy

63.86%

Latency

595.62s

Cost (In/Out)

0.3 / 2.4

Context Window

197k

Max Output Tokens

197k

Input Modality

Hyperparameter settings
Default Provider : MiniMax

Temperature

1

Top P

0.95

Top K

Default

Max Output Tokens

196,608

Benchmarks

Accuracy

Rankings

Vals Index

0.0%

14/ 28

CaseLaw (v2)

0.0%

39/ 63

CorpFin

0.0%

32/ 82

ProofBench

0.0%

15/ 15

TaxEval (v2)

0.0%

54/ 91

AIME

0.0%

17/ 82

GPQA

0.0%

15/ 85

LiveCodeBench

0.0%

24/ 90

LegalBench

0.0%

43/ 104

MedQA

0.0%

27/ 90

MMLU Pro

0.0%

41/ 84

SWE-bench

0.0%

8/ 50

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.