Model record

GPT-5.4 nano

xhigh

OpenAI · released Mar 17, 2026

Overall standing

Overall
48.5rank 33 of 63
48.5 is at approximately the 48th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 49.4.
8 of 8 measured
Category standingsReasoning 62.5Coding 53.8Math 9.3Agentic 21.0
Reasoning
62.5rank 39 of 63
62.5 is at approximately the 39th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 65.0.
4 of 4 measured
Coding
53.8rank 33 of 63
53.8 is at approximately the 48th percentile of the ranked Coding field. The field spans 10.4 to 72.4, with a median of 54.5.
2 of 2 measured
Math
9.3rank 27 of 63
9.3 is at approximately the 58th percentile of the ranked Math field. The field spans 0.0 to 32.3, with a median of 5.7.
1 of 1 measured
Agentic
21.0rank 27 of 63
21.0 is at approximately the 58th percentile of the ranked Agentic field. The field spans 3.3 to 33.4, with a median of 19.0.
1 of 1 measured
Model factsProprietary · $0.20 / $1.3 per 1M

Model facts come from the provider page. Listed API prices carry a separate first-party source and check date.

Provider
OpenAI
Released
Weights
Proprietary
Context window
400,000 tokens
Input price / Mtok
$0.20
Output price / Mtok
$1.3
Price source
Official pricing (opens in a new tab)
Reasoning effort
xhigh effort

Scores and sources

Measured scores retain their source and retrieval date. Missing scores are not treated as zero.

Benchmark scores, evaluation settings, sources, and retrieval dates for GPT-5.4 nano
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding60.7Artificial Analysis independent run; 89 tasks; Terminus 2 on E2B; 3 repeats; pass@1; 250-episode cap; 2-hour timeoutOpen source (opens in a new tab)
τ³-BankingAgentic21.0Artificial Analysis independent run; 97 tasks; 5 repeats; backend-state pass@1; BM25 plus grep retrieval; 200-step capOpen source (opens in a new tab)
AA-LCRReasoning66.0Artificial Analysis independent run; 100 roughly 100k-token multi-document questions; 3 repeats; equality-checker pass@1; no toolsOpen source (opens in a new tab)
Humanity's Last ExamReasoning26.5Artificial Analysis independent run; 2,158 text-only questions; pass@1; GPT-4o (August 2024) equality checker; no toolsOpen source (opens in a new tab)
GPQA DiamondReasoning81.7Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding46.9Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning75.9Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1Open source (opens in a new tab)
CritPtMath9.3Artificial Analysis independent run; 70 test challenges; 5 repeats; two-step answer parsing; official CritPt grader; pass@1; no toolsOpen source (opens in a new tab)