VerdictPal
Join

Models / OpenAI

GPT-5.1 Codex (high)

GPT-5.1 Codex · Released 2025-11-13

AA Intelligence Index 34.7. Listed on Artificial Analysis with API pricing $1.25/$10 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.

#91 of 184 on AA Index · current snapshot
24 AA Index · 11 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite62
Context128K
Input / 1M$1.3
Output / 1M$10
Knowledge cutoffopen
Statussolid

Family profile

Best published score in each covered benchmark family.

76/100 avg
Knowledge
86
Reasoning
86
Math
96
Coding
85
Agentic
35
Long context
69

6 tested benchmark families

Benchmark placements

Where GPT-5.1 Codex (high) 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
AIMEMath#6/ 3796Artificial Analysis2026-09-10
LiveCodeBenchCoding#12/ 3185Artificial Analysis2026-09-10
MMLU-ProKnowledge#19/ 3986Artificial Analysis2026-09-10
IFBenchReasoning#56/ 12770Artificial Analysis2026-09-10
GPQA DiamondReasoning#90/ 19086Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#99/ 18824Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#103/ 18526Artificial Analysis2026-09-10
AA-LCRLong context#125/ 18269Artificial Analysis2026-09-10
AA output speedPerformance#130/ 190Artificial Analysis2026-09-10
AA time to first tokenPerformance#130/ 190Artificial Analysis2026-09-10
Terminal-BenchAgentic#138/ 18935Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where GPT-5.1 Codex (high) shows up, it's highlighted.

KnowledgeGPT-5.1 Codex (high) · 86
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningGPT-5.1 Codex (high) · 86
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
MathGPT-5.1 Codex (high) · 96
  1. 1
    OpenAI o3
    99
  2. 2
    GPT-5 (medium)
    99
  3. 3
    Grok 4
    99
CodingGPT-5.1 Codex (high) · 85
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGPT-5.1 Codex (high) · 35
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGPT-5.1 Codex (high) · 69
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

Benchmark rows added to the public ledger for GPT-5.1 Codex (high) in the last 120 days. Older rows live in the full table below.

11 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context69.33%Artificial Analysis4
AA output speedPerformance0 t/sArtificial Analysis4
AA time to first tokenPerformance0.00sArtificial Analysis4
AIMEMath95.67%Artificial Analysis4
Artificial Analysis Intelligence IndexReasoning23.7%Artificial Analysis4
GPQA DiamondReasoning86%Artificial Analysis4
Humanity's Last ExamReasoning25.7%Artificial Analysis4
IFBenchReasoning70%Artificial Analysis4
LiveCodeBenchCoding84.9%Artificial Analysis4
MMLU-ProKnowledge86%Artificial Analysis4
Terminal-BenchAgentic34.85%Artificial Analysis4
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.

Knowledge86
Reasoning86
Math96
Coding85
Agentic35
Long context69
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for GPT-5.1 Codex (high). Scores link to the original source; gaps mean no public row exists yet.

11 sourced rows

11 of 37 catalog benchmarks have a sourced row for GPT-5.1 Codex (high).

Knowledge

Reasoning

Math

Coding

Agentic

Long context

Performance

Sources