VerdictPal
Join

Models / OpenAI

GPT-5.3 Codex (xhigh)

GPT-5.3 Codex · Released 2026-02-05

AA Intelligence Index 44.3. Listed on Artificial Analysis with API pricing $1.75/$14 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.

#14 of 51 on AA Index · current snapshot
44 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite64
Context128K
Input / 1M$1.8
Output / 1M$14
Knowledge cutoffopen
Output speed127 t/s
TTFT (default API)41.56s
Statussolid
ReasoningCodingAgenticLong context
Reasoning
92
Coding
53
Agentic
86
Long context
74

76average across 4 tested families

Benchmark placements

Where GPT-5.3 Codex (xhigh) 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
AA-LCRLong context#4/ 6474Artificial Analysis2026-07-21
τ³-Bench BankingAgentic#7/ 6486Artificial Analysis2026-07-21
AA time to first tokenPerformance#9/ 69Artificial Analysis2026-07-21
GPQA DiamondReasoning#14/ 6992Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#16/ 6540Artificial Analysis2026-07-21
SciCodeCoding#17/ 6553Artificial Analysis2026-07-21
AA output speedPerformance#20/ 69Artificial Analysis2026-07-21
IFBenchReasoning#20/ 5775Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#23/ 6744Artificial Analysis2026-07-21
Terminal-BenchAgentic#44/ 6953Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where GPT-5.3 Codex (xhigh) shows up, it's highlighted.

ReasoningGPT-5.3 Codex (xhigh) · 92
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
CodingGPT-5.3 Codex (xhigh) · 53
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGPT-5.3 Codex (xhigh) · 86
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGPT-5.3 Codex (xhigh) · 74
  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-5.3 Codex (xhigh) in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context74%Artificial Analysis2
AA output speedPerformance127 t/sArtificial Analysis2
AA time to first tokenPerformance41.56sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning44.3%Artificial Analysis2
GPQA DiamondReasoning91.5%Artificial Analysis2
Humanity's Last ExamReasoning39.9%Artificial Analysis2
IFBenchReasoning75.37%Artificial Analysis2
SciCodeCoding53.2%Artificial Analysis2
τ³-Bench BankingAgentic85.96%Artificial Analysis2
Terminal-BenchAgentic53.03%Artificial Analysis2
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.

Reasoning92
Coding53
Agentic86
Long context74
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-5.3 Codex (xhigh). Scores link to the original source; gaps mean no public row exists yet.

10 sourced rows

10 of 32 catalog benchmarks have a sourced row for GPT-5.3 Codex (xhigh).

Reasoning

Coding

Agentic

Long context

Performance

Sources