LLM

GPT-5.4 nano (medium)

Name: GPT-5.4 nano (medium) Review & Benchmarks
Item: GPT-5.4 nano (medium)
Rating: 38.1
Author: Sentient Weekly

by OpenAI

Overall Score

38.1

Released Mar 2026

Benchmark Scores

Reasoning

—

Coding

35.0

Math

—

Creative writing

—

Instruction following

—

Multimodal

—

Standard Benchmarks

aa_gpqaaa_gpqa

0.8

Measured 2026-05-13 · source

aa_hleaa_hle

0.1

Measured 2026-05-13 · source

aa_scicodeaa_scicode

0.4

Measured 2026-05-13 · source

aa_ifbenchaa_ifbench

0.6

Measured 2026-05-13 · source

aa_lcraa_lcr

0.6

Measured 2026-05-13 · source

aa_terminalbench_hardaa_terminalbench_hard

0.3

Measured 2026-05-13 · source

aa_tau2aa_tau2

0.5

Measured 2026-05-13 · source

Price

—

Context

—

Speed

159.54 t/s

4439ms TTFT

Compare this model →

Discussion

0 comments

Be the first to comment.