VerdictPal
Join

Models / OpenAI

GPT-5.4 (low)

GPT-5.4 (low) · Released 2026-03-05

AA Intelligence Index 39.1. Listed on Artificial Analysis with API pricing $2.5/$15 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#62 of 168 on AA Index · current snapshot
40 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite56
Context128K
Input / 1M$2.5
Output / 1M$15
Knowledge cutoffopen
Statussolid

Family profile

Best published score in each covered benchmark family.

64/100 avg
Reasoning
87
Coding
50
Agentic
43
Long context
74

4 tested benchmark families

Benchmark placements

Where GPT-5.4 (low) places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
SciCodeCoding#40/ 18050Artificial Analysis2026-09-01
AA-LCRLong context#59/ 17974Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#68/ 18031Artificial Analysis2026-09-01
IFBenchReasoning#69/ 12766Artificial Analysis2026-09-01
GPQA DiamondReasoning#72/ 18587Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#74/ 18740Artificial Analysis2026-09-01
Terminal-BenchAgentic#105/ 18443Artificial Analysis2026-09-01
AA time to first tokenPerformance#134/ 186Artificial Analysis2026-09-01
AA output speedPerformance#135/ 187Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where GPT-5.4 (low) shows up, it's highlighted.

ReasoningGPT-5.4 (low) · 87
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingGPT-5.4 (low) · 50
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGPT-5.4 (low) · 43
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGPT-5.4 (low) · 74
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

Benchmark rows added to the public ledger for GPT-5.4 (low) in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context73.67%Artificial Analysis5
AA output speedPerformance0 t/sArtificial Analysis5
AA time to first tokenPerformance0.00sArtificial Analysis5
Artificial Analysis Intelligence IndexReasoning40.2%Artificial Analysis5
GPQA DiamondReasoning87.1%Artificial Analysis5
Humanity's Last ExamReasoning30.8%Artificial Analysis5
IFBenchReasoning65.92%Artificial Analysis5
SciCodeCoding50.3%Artificial Analysis5
Terminal-BenchAgentic43.18%Artificial Analysis5
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning87
Coding50
Agentic43
Long context74
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for GPT-5.4 (low). Scores link to the original source; gaps mean no public row exists yet.

9 sourced rows

9 of 37 catalog benchmarks have a sourced row for GPT-5.4 (low).

Reasoning

Coding

Agentic

Long context

Performance

Sources