OpenAI model product
o1
o1 is an OpenAI research preview model focused on mathematical and logical reasoning.
Updated Sep 8, 2026. Default version: o1
LLMBoard Score35.3o1
Coverage40%16 benchmark families
Context window200KTokens
Official input price$15OpenAI API
o1 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
o1 Benchmark Results
Benchmark scores for o1.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkGPQA Biology | Score69.20% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGPQA Chemistry | Score64.70% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGPQA Physics | Score92.80% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMATH | Score96.40% | Rank02 | Participants71 | Percentile98.57% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score91.80% | Rank02 | Participants101 | Percentile99.00% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score97.10% | Rank03 | Participants48 | Percentile95.74% | EvidenceC | Evaluated |
| BenchmarkMGSM | Score89.30% | Rank10 | Participants31 | Percentile70.00% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score70.80% | Rank10 | Participants25 | Percentile62.50% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score71.80% | Rank12 | Participants39 | Percentile71.05% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score50.00% | Rank12 | Participants23 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkFrontierMath | Score5.50% | Rank17 | Participants17 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score47.00% | Rank17 | Participants47 | Percentile65.22% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score87.70% | Rank19 | Participants49 | Percentile62.50% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score77.60% | Rank19 | Participants64 | Percentile71.43% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score88.10% | Rank26 | Participants66 | Percentile61.54% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score67.00% | Rank33 | Participants38 | Percentile13.51% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score74.30% | Rank35 | Participants53 | Percentile34.62% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,193.10 rating | Rank67 | Participants107 | Percentile37.74% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,168.41 rating | Rank72 | Participants107 | Percentile33.02% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Verified | Score41.00% | Rank103 | Participants113 | Percentile8.93% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score78.00% | Rank105 | Participants247 | Percentile57.72% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,401.97 rating | Rank107 | Participants210 | Percentile49.28% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,365.61 rating | Rank126 | Participants210 | Percentile40.19% | EvidenceA | Evaluated |
o1 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision style control | Categorychinese | Rank45 | Rating / score1,262.74 | Votes99 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank46 | Rating / score1,409.41 | Votes396 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank50 | Rating / score1,395.96 | Votes396 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank56 | Rating / score1,234.28 | Votes99 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank67 | Rating / score1,193.10 | Votes3,694 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank72 | Rating / score1,168.41 | Votes3,694 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank72 | Rating / score1,186.48 | Votes1,943 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank73 | Rating / score1,374.40 | Votes581 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank77 | Rating / score1,162.11 | Votes1,943 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank85 | Rating / score1,389.62 | Votes5,210 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank86 | Rating / score1,346.12 | Votes581 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank87 | Rating / score1,397.52 | Votes7,663 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank91 | Rating / score1,406.88 | Votes10,246 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank94 | Rating / score1,380.97 | Votes4,642 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank99 | Rating / score1,408.81 | Votes2,986 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank101 | Rating / score1,414.01 | Votes2,644 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank102 | Rating / score1,412.06 | Votes3,571 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank105 | Rating / score1,389.33 | Votes11,491 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank105 | Rating / score1,392.77 | Votes142 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank106 | Rating / score1,385.92 | Votes19,214 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank107 | Rating / score1,357.99 | Votes5,210 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank107 | Rating / score1,406.75 | Votes1,454 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank107 | Rating / score1,401.97 | Votes27,807 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank109 | Rating / score1,429.34 | Votes1,780 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank109 | Rating / score1,374.70 | Votes556 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank110 | Rating / score1,367.43 | Votes10,246 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank110 | Rating / score1,411.63 | Votes16,316 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank110 | Rating / score1,417.62 | Votes6,453 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank111 | Rating / score1,386.65 | Votes3,078 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank112 | Rating / score1,347.30 | Votes4,642 | ObservationsN/A | Result date |
o1 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $15 input, $60 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- N/A
- Tracked offerings
- 1
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOpenAI | Provider model IDo1 | Regionglobal | Input / 1M$15 | Output / 1M$60 | Context200K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
o1 Runtime Performance
Provider-specific output speed and catalog latency for o1. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed66.00 tok/s | Catalog Latency16.20 s | Max Input200K | Max Output100K | Updated |
| ProviderAzure | Output Speed16.00 tok/s | Catalog Latency0.54 s | Max Input200K | Max Output100K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
o1 Specifications
Technical details for the model's default version.
- Version
- o1
- Released
- Dec 17, 2024
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 200K
- Max output
- 100K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
o1 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| Versiono1 | Released | LLMBoard35.26 | ParametersN/A | Context200K | Max output100K | Open weightsNo | LicenseProprietary |
| Versiono1-preview | Released | LLMBoardN/A | ParametersN/A | Context128K | Max output32.8K | Open weightsNo | LicenseProprietary |
Models similar to o1
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-4.5
OpenAI
OP
o3 mini
OpenAI
OP
o1 pro
OpenAI
OP
GPT-4.1
OpenAI
OP
GPT-5-Nano
OpenAI
OP
GPT-5.3
OpenAI
What is o1?
Key information about o1 and its available data.
o1 is a large language model for tasks involving step-by-step reasoning, mathematical problem-solving, and code generation. It demonstrates enhanced formal reasoning while maintaining general capabilities.
Data as of 2026-09-08.
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 was created by OpenAI.
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 provider offerings are linked to the default version.