OpenAI model product
o3
OpenAI's most powerful reasoning model.
Updated Aug 17, 2026. Default version: o3
LLMBoard Score52.4o3
Coverage100%22 benchmark families
Context window200KTokens
Official input price$2OpenAI API
o3 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
o3 Benchmark Results
Benchmark scores for o3.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAider-Polyglot | Score81.3% | Rank03 | Participants22 | Percentile90.5% | EvidenceC | Evaluated |
| BenchmarkCOLLIE | Score98.4% | Rank03 | Participants10 | Percentile77.8% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score86.8% | Rank03 | Participants39 | Percentile94.7% | EvidenceC | Evaluated |
| BenchmarkARC-AGI | Score88.0% | Rank04 | Participants8 | Percentile57.1% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score91.6% | Rank06 | Participants53 | Percentile90.4% | EvidenceC | Evaluated |
| BenchmarkTau-bench | Score63.0% | Rank06 | Participants6 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score82.9% | Rank07 | Participants63 | Percentile90.3% | EvidenceC | Evaluated |
| BenchmarkTau2 Retail | Score80.2% | Rank08 | Participants26 | Percentile72.0% | EvidenceC | Evaluated |
| BenchmarkTau2 Airline | Score64.8% | Rank09 | Participants23 | Percentile63.6% | EvidenceC | Evaluated |
| BenchmarkERQA | Score64.0% | Rank10 | Participants24 | Percentile60.9% | EvidenceC | Evaluated |
| BenchmarkMulti-Challenge | Score60.4% | Rank10 | Participants29 | Percentile67.9% | EvidenceC | Evaluated |
| BenchmarkFrontierMath | Score15.8% | Rank13 | Participants17 | Percentile25.0% | EvidenceC | Evaluated |
| BenchmarkVideoMMMU | Score83.3% | Rank13 | Participants26 | Percentile52.0% | EvidenceC | Evaluated |
| BenchmarkARC-AGI v2 | Score6.5% | Rank16 | Participants17 | Percentile6.3% | EvidenceB | Evaluated |
| BenchmarkCharXiv-R | Score78.6% | Rank25 | Participants51 | Percentile52.0% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score76.4% | Rank28 | Participants68 | Percentile59.7% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score58.2% | Rank30 | Participants35 | Percentile14.7% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score49.7% | Rank46 | Participants62 | Percentile26.2% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score86.4% | Rank58 | Participants115 | Percentile50.0% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score69.1% | Rank70 | Participants111 | Percentile37.3% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score83.3% | Rank71 | Participants239 | Percentile70.6% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score14.7% | Rank77 | Participants99 | Percentile22.4% | EvidenceC | Evaluated |
o3 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenasearch style control | Categoryoverall | Rank15 | Rating / score1190.9 | Votes20,785 | ObservationsN/A | Result date |
| Arenasearch | Categoryoverall | Rank24 | Rating / score1143.5 | Votes20,785 | ObservationsN/A | Result date |
| Arenasearch factuality | Categoryoverall | Rank30 | Rating / score1128.1 | Votes3,706 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank62 | Rating / score1216.8 | Votes46,095 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank65 | Rating / score1215.3 | Votes46,095 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank92 | Rating / score1430.7 | Votes59,899 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank120 | Rating / score1409.3 | Votes59,899 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank129 | Rating / score1403.3 | Votes7,585 | ObservationsN/A | Result date |
o3 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $2 input, $8 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $1.8 input, $7.2 output per 1M via Poe
- Tracked offerings
- 12
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderPoe | Provider model IDopenai/o3 | Regionglobal | Input / 1M$1.8 | Output / 1M$7.2 | Context200K | Updated |
| ProviderNanoGPT | Provider model IDopenai/o3 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context200K | Updated |
| ProviderImpossibl | Provider model IDopenai/o3 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context200K | Updated |
| ProviderOpenRouter | Provider model IDopenai/o3 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context200K | Updated |
| ProviderOpenAI | Provider model IDo3 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context200K | Updated |
| ProviderNEAR AI Cloud | Provider model IDopenai/o3 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context200K | Updated |
| ProviderMerge Gateway | Provider model IDopenai/o3 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context200K | Updated |
| ProviderCloudflare AI Gateway | Provider model IDopenai/o3 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context200K | Updated |
| ProviderVercel AI Gateway | Provider model IDopenai/o3 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context200K | Updated |
| ProviderEden AI | Provider model IDopenai/o3 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context200K | Updated |
| ProviderKilo Gateway | Provider model IDopenai/o3 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context200K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
o3 Runtime Performance
Provider-specific output speed and catalog latency for o3. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed50 tok/s | Catalog Latency20 s | Max Input200K | Max Output100K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
o3 Specifications
Technical details for the model's default version.
- Version
- o3
- Released
- Apr 16, 2025
- Knowledge cutoff
- May 31, 2024
- Parameters
- N/A
- Context window
- 200K
- Max output
- 100K
- Inputs
- image, pdf, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
o3 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 |
|---|
| Versiono3 | Released | LLMBoard52.4 | ParametersN/A | Context200K | Max output100K | Open weightsNo | LicenseProprietary |
o3 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to o3
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-5.5-Instant
OpenAI
OP
GPT-5.1-Codex
OpenAI
OP
GPT-5
OpenAI
OP
GPT-5.4-nano
OpenAI
OP
GPT-OSS-20B
OpenAI
OP
GPT-5.2-Codex
OpenAI
What is o3?
Key information about o3 and its available data.
OpenAI's most powerful reasoning model. o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following.
Use it to think through multi-step problems that involve analysis across text, code, and images.
Data as of 2026-08-17.
FAQ
Common questions about o3.
When was o3 released?
o3's default version was released on Apr 16, 2025.
How much does o3 cost?
o3's official API price is $2 per million input tokens and $8 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $1.8 input and $7.2 output via Poe.
Who created o3?
o3 was created by OpenAI.
What is the context window for o3?
The default version has a 200K token context window.
Is o3 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer o3?
12 provider offerings are linked to the default version.
What models should I compare o3 with?
Nearby ranked alternatives include Grok 4 Fast, MiniMax M2.1, Seed 2.0 Lite.