GPT-5.4
Still widely deployed prior GPT-5 generation — strong computer-use and coding history, often cheaper via existing contracts.
When to use it
Teams already on GPT-5.x infra who need stability over bleeding edge.
Watch-outs
Superseded by 5.5/5.6 on preference and newest composites.
Benchmarks
Human preference ranking from blind pairwise chats. Higher is better; top frontier models cluster within ~50–80 Elo.
Artificial Analysis composite across agents, coding, science, and general evaluations (v4.1 weighting).
Percent of real GitHub issues resolved end-to-end. Strong signal for agentic coding usefulness.
PhD-level science questions. Separates frontier reasoning models better than saturated knowledge tests.
Harder multi-choice knowledge/reasoning suite than classic MMLU.
Frontier closed-ended academic difficulty across many domains.
More from OpenAI
- GPT-5.6 SolAA 59
General frontier reasoning, mixed multimodal apps, and OpenAI ecosystem tooling.
- GPT-5.5 ProAA 55
Hard reasoning tasks, research assistants, and multimodal product surfaces.
- GPT-5.5AA 51
Default production chat, tools, and mixed workloads on OpenAI.