llm.ing

GPT-5.4

OpenAIOpenRouter ↗Artificial Analysis ↗

Agent-ready GPT for coding and computer-use workflows at a lower cost

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Agentic Indexagentic41.1mirroropenrouterJul 23, 2026
AA Coding Indexcoding71.1mirroropenrouterJul 23, 2026
AA Intelligence Indexintelligence51.4mirroropenrouterJul 23, 2026
27.7non-reasoningindependentaaJul 24, 2026
Design Arena — 3dpreference1161mirroropenrouterJul 23, 2026
Design Arena — androidnativepreference1015mirroropenrouterJul 24, 2026
Design Arena — asciiartpreference1240mirroropenrouterJul 23, 2026
Design Arena — codecategoriespreference1244mirroropenrouterJul 24, 2026
Design Arena — datavizpreference1266mirroropenrouterJul 24, 2026
Design Arena — fullstackpreference1075mirroropenrouterJul 23, 2026
Design Arena — gamedevpreference1298mirroropenrouterJul 23, 2026
Design Arena — godotgamedevpreference1135mirroropenrouterJul 23, 2026
Design Arena — mobileappspreference1147mirroropenrouterJul 23, 2026
Design Arena — svgpreference1243mirroropenrouterJul 23, 2026
Design Arena — uicomponentpreference1280mirroropenrouterJul 23, 2026
Design Arena — webappspreference1122mirroropenrouterJul 23, 2026
Design Arena — websitepreference1247mirroropenrouterJul 23, 2026
LMArena Textpreference1494high-effortcrowdlmarenaJul 21, 2026
1499crowdlmarenaJul 21, 2026
LMArena Visionpreference1299high-effortcrowdlmarenaJul 21, 2026
1290crowdlmarenaJul 21, 2026
LMArena WebDevpreference1386crowdlmarenaJul 21, 2026
Median output speedspeed88 tok/snon-reasoningindependentaaJul 24, 2026
Median time to first tokenspeed0.79snon-reasoningindependentaaJul 24, 2026

Includes index data from Artificial Analysis.

Providers

Live operational stats per hosting endpoint, via OpenRouter.

ProviderQuantContext$/1M in · outUptime 24hLatencyThroughput
Azure1.1M$2.5 · $15100.00%
Azure1.1M$2.75 · $16.5100.00%
OpenAI1.1M$2.5 · $1599.21%
OpenAI1.1M$1.25 · $7.599.21%
OpenAI1.1M$5 · $3099.21%