Models/o1

MDL

o1

OpenAI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$15 / $60

in / out

Context

200K

tokens

Avg score

59.7

12 benchmarks

AA Intelligence

23.4

index

Speed

139 tok/s

TTFT 16s

Released

Dec 5, 2024

About

o1 is a proprietary model in the o1 family from OpenAI. Benchmarked on 12 evals, averaging 59.7.

proprietarytextvision

Benchmark scores · 12

avg 59.7 — higher is better

MATHartificial-analysis · 2026-07

MMLUvendor-reported · 2024-12

91.8

MMLU-Proartificial-analysis · 2026-07

84.1

GPQA Diamondvendor-reported · 2024-12

IFBenchartificial-analysis · 2026-07

70.3

LiveCodeBenchartificial-analysis · 2026-07

67.9

τ²-benchartificial-analysis · 2026-07

62.6

AA Long-Context Reasoningartificial-analysis · 2026-07

59.3

SWE-bench Verifiedvendor-reported · 2024-12

48.9

SciCodeartificial-analysis · 2026-07

35.8

Terminal-Bench Hardartificial-analysis · 2026-07

12.9

Humanity's Last Examartificial-analysis · 2026-07

7.7

Details

PublisherOpenAI

Familyo1

Parameters—

Licenseproprietary

WeightsClosed

ReleasedDec 5, 2024

Performance & price

Output speed139 tok/s

Latency (TTFT)16s

Price in / out$15 / $60 per 1M

Blended price$26.25 / 1M

Coding index39.7

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$60/M

OpenAI200K ctx · $60/M