OpenAIProvisional

GPT-5.4 mini

GPT-5.4 / mini · gpt-5.4-mini

OpenAI mini model for coding, computer use, subagents, and lower-latency workflows.

Objective score

26.7

Confidence

79%

Price evidence

Pricing evidence pending

Support this model Compare trend Official source

Other primary tiers in this family

Defaultmininano

Scenario evidence

Six task-specific rankings

Feature development#47Obj. 26.70 · 0%Debug and repair#43Obj. 420 · 0%Refactoring#39Obj. 420 · 0%Code review#39Obj. 43.50 · 0%Large-repo agent work#46Obj. 22.60 · 0%Frontend / UI#39Obj. 420 · 0%

Evidence state

Signal coverage

Benchmarks: 2
Rank points: 7
Usage: 2
Agent: 0
Sources: 3

Objective evidence

Benchmarks and public signals

Swebench: —
Livecodebench: —
Aider: —
Artificial Analysis: 56.1
Openrouter Usage: 0.2
Kilo Usage: —

Persistent history

Recent ranking points

Sep 15#48 · 28

Sep 15#48 · 28

Sep 15#48 · 28

Sep 14#48 · 28

Sep 14#48 · 28

Sep 14#48 · 28

Usage signals

OpenRouter0.2%

Overall0.2%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.

Source trail

OpenAI model catalog lists GPT-5.4 mini for coding, computer use, and subagents.Artificial Analysis Coding Agents · ok WebDev Arena · ok OpenRouter rankings · ok