Compare Models
GPT 5.2 Codex

Release Date: Dec 11, 2025

Developer OpenAI 🇺🇸
Context Window 400k
Max Output Tokens 128k
Token Costs (in/out) $1.75/14.00
Weights Private
Input Modalities

Accuracy

66.10 %

Avg. Cost (In/Out)

$ 1.75 / $ 14.00

Latency

12 min 44 s

Vals Index
BenchmarksAccuracyRankings
Vibe Code Bench v1.1

0.0%

±4.58
50/96
LiveCodeBench

0.0%

±0.94
9/143
SWE-bench

0.0%

±2.00
55/88
Proprietary BenchmarksAcademic BenchmarksIndustry Partners
Vals
Default Provider : OpenAI
Temperature: Default
Top P: Default
Top K: Default
Max Output Tokens: 128,000
Reasoning Effort: high