Compare AI models

Specifications
Parameters
671B—
Context window
128k400k
API pricing
Cheapest input
$0.256DeepInfra$1.25Azure
Cheapest output
$0.712DeepInfra$10.00Azure
$103StreamLake$750Azure
Benchmarks
SWE-Bench Verified
42%77.9%
Overview
CompanyDeepSeekOpenAI
Release dateDec 26 2024Nov 19 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GPT-5.1-Codex-Max leads DeepSeek V3 on 1 of the 1 benchmark they both report (SWE-Bench Verified). DeepSeek V3 shipped 328 days before GPT-5.1-Codex-Max, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 400k (GPT-5.1-Codex-Max). DeepSeek V3 is open weight, while GPT-5.1-Codex-Max is closed.

On SWE-Bench Verified, GPT-5.1-Codex-Max leads at 77.9% vs DeepSeek V3 at 42%.