llm.ing

GPT-5.2 Codex

OpenAIOpenRouter ↗Artificial Analysis ↗

Code-specialist GPT for repository edits, reviews, and long-running software agents

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Intelligence Indexintelligence28.5—independentaaSep 9, 2026
28.5—mirroropenrouterOct 5, 2026
Design Arena — androidnativepreference1176—mirroropenrouterJul 23, 2026
Design Arena — fullstackpreference963—mirroropenrouterNov 19, 2026
Design Arena — godotgamedevpreference1142—mirroropenrouterJul 23, 2026
Design Arena — mobileappspreference1081—mirroropenrouterNov 15, 2026
Design Arena — webappspreference1042—mirroropenrouterOct 17, 2026
1029—mirroropenrouterNov 19, 2026
LMArena WebDevpreference1339—crowdlmarenaNov 11, 2026
Median output speedspeed132 tok/s—independentaaNov 19, 2026
Median time to first tokenspeed84.07s—independentaaNov 19, 2026

Includes index data from Artificial Analysis.

Providers

Live operational stats per hosting endpoint, via OpenRouter.

ProviderQuantContext$/1M in · outUptime 24hLatencyThroughput
Azure—400K$1.75 · $14100.00%——