all the models — AI benchmark observatory
← Models

GPT-5.4 nano

OpenAI · proprietary · gpt-5.4-nano

GPT-5.4 nano is OpenAI's cheapest GPT-5.4-class model for simple high-volume tasks. It is optimized for classification, data extraction, ranking, and lightweight coding subagents, while preserving strong reasoning, multimodal understanding, and tool use for latency-sensitive workloads.

Tau2 TelecomGPQAMMMU-ProHumanity's L

Benchmark scores

BenchmarkScore
Tau2 Telecom0.93
GPQA0.83
MMMU-Pro0.66
Humanity's Last Exam0.24

Pricing

  • OpenAI$0.20 / $1.25

Input / output per 1M tokens

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.