Models/GPT-4o (Nov '24)

MDL

GPT-4o (Nov '24)

OpenAI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$2.5 / $10

in / out

Context

—

Avg score

31.5

11 benchmarks

AA Intelligence

11.2

index

Speed

210 tok/s

TTFT 0.5s

Released

Nov 20, 2024

About

GPT-4o (Nov '24) is a proprietary model in the GPT family from OpenAI. Benchmarked on 11 evals, averaging 31.5.

Benchmark scores · 11

avg 31.5 — higher is better

MATHartificial-analysis · 2026-07

75.9

MMLU-Proartificial-analysis · 2026-07

74.8

GPQA Diamondartificial-analysis · 2026-07

54.3

IFBenchartificial-analysis · 2026-07

34.3

SciCodeartificial-analysis · 2026-07

33.3

LiveCodeBenchartificial-analysis · 2026-07

30.9

τ²-benchartificial-analysis · 2026-07

25.1

Terminal-Bench Hardartificial-analysis · 2026-07

8.3

AIMEartificial-analysis · 2026-07

Humanity's Last Examartificial-analysis · 2026-07

3.3

AA Long-Context Reasoningartificial-analysis · 2026-07

Details

PublisherOpenAI

FamilyGPT

Parameters—

License—

WeightsClosed

ReleasedNov 20, 2024

Performance & price

Output speed210 tok/s

Latency (TTFT)0.5s

Price in / out$2.5 / $10 per 1M

Blended price$4.38 / 1M

Math index6.0

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