GPT 5.2

Release Date: 12/11/2025

Benchmarked by Vals Logo
Vals Index

GPT-5.2 is OpenAI's most advanced frontier model for everyday professional use and agentic tasks, with leading long-context reasoning, multi-step tool use, and vision capabilities.

Avg. Accuracy

71.63%

Latency

1345.47s

Cost (In/Out)

1.75 / 14

Context Window

400k

Max Output Tokens

128k

Input Modality

Benchmarks

Accuracy

Rankings

Vals Index

0.0%

26/ 26

CaseLaw (v2)

0.0%

54/ 54

CorpFin

0.0%

76/ 76

Finance Agent

0.0%

54/ 54

MortgageTax

0.0%

55/ 55

SAGE

0.0%

35/ 35

TaxEval (v2)

0.0%

83/ 83

Vibe Code Bench

0.0%

15/ 15

AIME

0.0%

73/ 73

GPQA

0.0%

74/ 74

IOI

0.0%

37/ 37

LiveCodeBench

0.0%

79/ 79

LegalBench

0.0%

97/ 97

MedQA

0.0%

81/ 81

MGSM

0.0%

70/ 70

MMLU Pro

0.0%

75/ 75

SWE-bench

0.0%

38/ 38

Terminal-Bench

0.0%

40/ 40

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.