llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelso1

OpenAI model product

o1

A research preview model focused on mathematical and logical reasoning capabilities, demonstrating improved performance on tasks requiring step-by-step reasoning, mathematical problem-solving, and code generation. The model shows enhanced capabilities in formal reasoning while maintaining strong general capabilities.

Updated Aug 10, 2026. Default version: o1

Compare
LLMBoard score63.0o1
Coverage80%9 benchmark families
Context window200KTokens
Official input price$15OpenAI API

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
o1
Released
Dec 17, 2024
Knowledge cutoff
Sep 1, 2023
Parameters
N/A
Context window
200K
Max output
100K
Inputs
image, pdf, text
Outputs
text
Open weights
No
License
Proprietary

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

o1 category scores

Benchmark results

Published benchmark records for the scored version o1.

19 rows
Columns

Show columns

GPQA Biology0.711100.0%CAug 7, 2026
GPQA Chemistry0.611100.0%CAug 7, 2026
GPQA Physics0.911100.0%CAug 7, 2026
MATH1.027198.6%CAug 7, 2026
MMLU0.9210099.0%CAug 7, 2026
GSM8k1.034895.7%CAug 7, 2026
MGSM0.9103170.0%CAug 7, 2026
TAU-bench Retail0.7102562.5%CAug 7, 2026
MathVista0.7123971.0%CAug 7, 2026
TAU-bench Airline0.5122350.0%CAug 7, 2026
FrontierMath0.117170.0%CAug 7, 2026
SimpleQA0.5174664.4%CAug 7, 2026
MMMU0.8186372.6%CAug 7, 2026
MMMLU0.9194962.5%CAug 7, 2026
HumanEval0.9287664.0%CAug 7, 2026
LiveBench0.7333813.5%CAug 7, 2026
AIME 20240.7355334.6%CAug 7, 2026
SWE-Bench Verified0.4941049.7%CAug 7, 2026
GPQA0.89523359.5%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

62 rows
Columns

Show columns

vision style controlchinese501261.999N/AAug 6, 2026
text style controlkorean521409.8396N/AAug 6, 2026
textkorean541396.6396N/AAug 6, 2026
visionchinese641230.699N/AAug 6, 2026
vision style controloverall761193.43,694N/AAug 6, 2026
vision style controlenglish811187.61,943N/AAug 6, 2026
text style controljapanese891375.1581N/AAug 6, 2026
visionoverall891168.63,694N/AAug 6, 2026
visionenglish951163.41,943N/AAug 6, 2026
textjapanese1021346.9581N/AAug 6, 2026
text style controlindustry entertainment and sports and media1051390.15,210N/AAug 6, 2026
text style controlinstruction following1111407.010,246N/AAug 6, 2026
text style controlindustry writing and literature and language1121397.67,663N/AAug 6, 2026
text style controlmath1201408.92,986N/AAug 6, 2026
text style controlcreative writing1211381.34,642N/AAug 6, 2026
text style controlindustry mathematical1241414.12,644N/AAug 6, 2026
text style controllonger query1281412.03,571N/AAug 6, 2026
text style controlspanish1281388.6142N/AAug 6, 2026
text style controlexclude ties1321386.319,214N/AAug 6, 2026
text style controlnon english1321389.611,491N/AAug 6, 2026
textindustry entertainment and sports and media1341358.65,210N/AAug 6, 2026
text style controloverall1341402.227,807N/AAug 6, 2026
text style controlindustry legal and government1351406.41,454N/AAug 6, 2026
text style controlchinese1361429.21,780N/AAug 6, 2026
text style controlenglish1381411.716,316N/AAug 6, 2026
text style controlgerman1401375.3556N/AAug 6, 2026
text style controlhard prompts1401417.86,453N/AAug 6, 2026
text style controlrussian1411386.73,078N/AAug 6, 2026
textinstruction following1421367.810,246N/AAug 6, 2026
textindustry mathematical1431389.52,644N/AAug 6, 2026
text style controlindustry life and physical and social science1441410.74,820N/AAug 6, 2026
textcreative writing1451347.84,642N/AAug 6, 2026
textindustry writing and literature and language1471360.07,663N/AAug 6, 2026
textlonger query1471378.03,571N/AAug 6, 2026
text style controlhard prompts english1481423.04,238N/AAug 6, 2026
textmath1491388.42,986N/AAug 6, 2026
text style controlexpert1511400.61,330N/AAug 6, 2026
textchinese1531393.61,780N/AAug 6, 2026
text style controlindustry software and it services1531423.06,584N/AAug 6, 2026
text style controlcoding1541433.03,973N/AAug 6, 2026
textnon english1551358.511,491N/AAug 6, 2026
textrussian1561355.03,078N/AAug 6, 2026
texthard prompts1571371.76,453N/AAug 6, 2026
text style controlfrench1571385.2252N/AAug 6, 2026
textgerman1591337.2556N/AAug 6, 2026
text style controlmulti turn1591386.04,399N/AAug 6, 2026
textexclude ties1601334.119,214N/AAug 6, 2026
textexpert1601360.81,330N/AAug 6, 2026
text style controlindustry medicine and healthcare1601398.41,273N/AAug 6, 2026
textoverall1621366.027,807N/AAug 6, 2026
textindustry legal and government1621368.31,454N/AAug 6, 2026
text style controlindustry business and management and financial operations1641369.92,720N/AAug 6, 2026
textfrench1651343.2252N/AAug 6, 2026
textspanish1661342.0142N/AAug 6, 2026
textindustry life and physical and social science1681369.14,820N/AAug 6, 2026
textmulti turn1691354.74,399N/AAug 6, 2026
texthard prompts english1721373.44,238N/AAug 6, 2026
textenglish1761372.216,316N/AAug 6, 2026
textindustry medicine and healthcare1761354.21,273N/AAug 6, 2026
textcoding1791367.43,973N/AAug 6, 2026
textindustry software and it services1791367.46,584N/AAug 6, 2026
textindustry business and management and financial operations1831327.42,720N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$15 input, $60 output per 1M
Official provider
OpenAI
Lowest third-party
N/A
Tracked offerings
1
1 rows
Columns

Show columns

OpenAIo1global$15$60200KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

o1 versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

2 rows
Columns

Show columns

o1Dec 17, 202463.0N/A200K100KNoProprietary
o1-previewSep 12, 2024N/AN/A128K32.8KNoProprietary

What is o1?

A concise description based on the published model registry.

A research preview model focused on mathematical and logical reasoning capabilities, demonstrating improved performance on tasks requiring step-by-step reasoning, mathematical problem-solving, and code generation. The model shows enhanced capabilities in formal reasoning while maintaining strong general capabilities.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

o1 vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

o1vsGemini 2.5 Flasho1vsNova Proo1vsMAI Thinking 1o1vsLlama 3.3 Nemotron Super 49Bo1vsLlama 3.1 Nemotron Ultra 253Bo1vsGLM 4.5

Models similar to o1

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#49-1.4
OP

o3 mini

OpenAI

61.6 LLMBoard

DetailsCompare
#56-4.2
OP

GPT-4.5

OpenAI

58.8 LLMBoard

DetailsCompare
#60-6.1
OP

GPT-OSS-120B

OpenAI

56.9 LLMBoard

DetailsCompare
#34+6.1
OP

GPT-5.2

OpenAI

69.1 LLMBoard

DetailsCompare
#61-6.4
OP

GPT-5.4-mini

OpenAI

56.5 LLMBoard

DetailsCompare
#64-7.2
OP

o3

OpenAI

55.8 LLMBoard

DetailsCompare

FAQ

Common questions about o1.

When was o1 released?

o1's default version was released on Dec 17, 2024.

How much does o1 cost?

o1's official API price is $15 per million input tokens and $60 per million output tokens via OpenAI.

Who created o1?

o1 is published under OpenAI in the model registry.

What is the context window for o1?

The default version has a 200K token context window.

Is o1 open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer o1?

1 published provider offerings are linked to the default version.

What models should I compare o1 with?

Nearby ranked alternatives include Gemini 2.5 Flash, Nova Pro, MAI Thinking 1.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai