VerdictPal
Join

Models / OpenAI

GPT-5.4 Mini

GPT-5.4 · Released 2026-03-17

OpenAI's March 2026 mid-tier. Best price/performance pick for production apps. $0.75/$4.50 per 1M tokens.

Cost-effective GPT-5.4 for production chatbots, code completions, and real-time applications.

#12 of 21 on Vals Index · current snapshot
51 Vals Index · 11 benchmark rows · 2 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite53
Context128K
Input / 1M$0.75
Output / 1M$4.5
Knowledge cutoff2026-01-01
Output speed180 t/s
TTFT (default API)8.20s
Statussolid
ReasoningCodingAgenticLong context
Reasoning
88
Coding
50
Agentic
59
Long context
69

67average across 4 tested families

Benchmark placements

Where GPT-5.4 Mini 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
Vals IndexAgentic#12/ 2051Vals AI — Vals Index2026-06-04
AA output speedPerformance#13/ 69Artificial Analysis2026-07-21
AA time to first tokenPerformance#22/ 69Artificial Analysis2026-07-21
IFBenchReasoning#25/ 5773Artificial Analysis2026-07-21
AA-LCRLong context#26/ 6469Artificial Analysis2026-07-21
SciCodeCoding#30/ 6550Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#33/ 6740Artificial Analysis2026-07-21
GPQA DiamondReasoning#34/ 6988Artificial Analysis2026-07-21
τ³-Bench BankingAgentic#37/ 6421Artificial Analysis2026-07-21
Terminal-BenchAgentic#39/ 6959Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#40/ 6527Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where GPT-5.4 Mini shows up, it's highlighted.

ReasoningGPT-5.4 Mini · 88
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
CodingGPT-5.4 Mini · 50
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGPT-5.4 Mini · 59
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGPT-5.4 Mini · 69
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
Newest receipts

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

11 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context69.33%Artificial Analysis2
AA output speedPerformance180 t/sArtificial Analysis2
AA time to first tokenPerformance8.20sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning40%Artificial Analysis2
GPQA DiamondReasoning87.5%Artificial Analysis2
Humanity's Last ExamReasoning26.6%Artificial Analysis2
IFBenchReasoning73.27%Artificial Analysis2
SciCodeCoding49.9%Artificial Analysis2
τ³-Bench BankingAgentic21.44%Artificial Analysis2
Terminal-BenchAgentic59.18%Artificial Analysis2
Vals IndexAgentic51.42%Vals AI — Vals Index49
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.

Reasoning88
Coding50
Agentic59
Long context69
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

Full benchmark ledger

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

11 sourced rows

11 of 32 catalog benchmarks have a sourced row for GPT-5.4 Mini.

Reasoning

Coding

Agentic

Long context

Performance

Changelog
  1. Released GPT-5.4 Mini — best price/performance, $0.75/$4.50.
Sources