Models/GPT-5.1 Codex

MDL

GPT-5.1 Codex

OpenAI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$1.25 / $10

in / out

Context

400K

tokens

Avg score

67.1

10 benchmarks

AA Intelligence

34.7

index

Speed

191 tok/s

TTFT 5.1s

Released

Nov 13, 2025

About

GPT-5.1 Codex is a proprietary model in the GPT family from OpenAI. Benchmarked on 10 evals, averaging 67.1.

Benchmark scores · 10

avg 67.1 — higher is better

AIMEartificial-analysis · 2026-07

95.7

GPQA Diamondartificial-analysis · 2026-07

MMLU-Proartificial-analysis · 2026-07

LiveCodeBenchartificial-analysis · 2026-07

84.9

τ²-benchartificial-analysis · 2026-07

IFBenchartificial-analysis · 2026-07

AA Long-Context Reasoningartificial-analysis · 2026-07

67.3

SciCodeartificial-analysis · 2026-07

40.2

Terminal-Bench Hardartificial-analysis · 2026-07

34.8

Humanity's Last Examartificial-analysis · 2026-07

23.4

Details

PublisherOpenAI

FamilyGPT

Parameters—

License—

WeightsClosed

ReleasedNov 13, 2025

Performance & price

Output speed191 tok/s

Latency (TTFT)5.1s

Price in / out$1.25 / $10 per 1M

Blended price$3.44 / 1M

Math index95.7

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers

Artificial Analysis$10/M