OpenAI model product
GPT-5.3
3 is an OpenAI language model used in ChatGPT that accepts text and image inputs with a 128k context window.
Updated Sep 8, 2026. Default version: GPT-5.3 Chat
LLMBoard Score41.1GPT-5.3 Chat
Coverage0%2 benchmark families
Context window128KTokens
Official input price$1.75OpenAI API
GPT-5.3 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-5.3 Benchmark Results
Benchmark scores for GPT-5.3 Chat.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkHealthBench Hard | Score25.90% | Rank06 | Participants9 | Percentile37.50% | EvidenceC | Evaluated |
| BenchmarkHealthBench | Score54.10% | Rank07 | Participants9 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,225.21 rating | Rank50 | Participants107 | Percentile53.77% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,231.55 rating | Rank52 | Participants107 | Percentile51.89% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,449.04 rating | Rank53 | Participants210 | Percentile75.12% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,422.16 rating | Rank84 | Participants121 | Percentile30.83% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,403.56 rating | Rank101 | Participants210 | Percentile52.15% | EvidenceA | Evaluated |
GPT-5.3 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorycreative writing | Rank11 | Rating / score1,239.48 | Votes1,518 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing | Rank12 | Rating / score1,231.82 | Votes1,518 | ObservationsN/A | Result date |
| Arenavision style control | Categorycaptioning | Rank14 | Rating / score1,197.78 | Votes382 | ObservationsN/A | Result date |
| Arenavision | Categorycaptioning | Rank15 | Rating / score1,214.49 | Votes382 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank25 | Rating / score1,472.94 | Votes730 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank25 | Rating / score1,187.31 | Votes370 | ObservationsN/A | Result date |
| Arenavision | Categoryentity recognition | Rank27 | Rating / score1,216.39 | Votes370 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank31 | Rating / score1,423.14 | Votes543 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank33 | Rating / score1,432.26 | Votes517 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank34 | Rating / score1,279.97 | Votes1,312 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank34 | Rating / score1,275.74 | Votes1,312 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank38 | Rating / score1,411.32 | Votes517 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank38 | Rating / score1,480.43 | Votes2,449 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank42 | Rating / score1,459.30 | Votes6,499 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank43 | Rating / score1,464.88 | Votes2,554 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank43 | Rating / score1,466.77 | Votes6,165 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank44 | Rating / score1,442.90 | Votes18,164 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank44 | Rating / score1,456.21 | Votes3,746 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank46 | Rating / score1,495.03 | Votes1,978 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank46 | Rating / score1,261.49 | Votes2,039 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank46 | Rating / score1,259.17 | Votes2,503 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank46 | Rating / score1,244.49 | Votes10,621 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank47 | Rating / score1,451.43 | Votes773 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank47 | Rating / score1,252.02 | Votes2,503 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank48 | Rating / score1,473.27 | Votes1,004 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank48 | Rating / score1,263.89 | Votes2,039 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank48 | Rating / score1,206.22 | Votes1,295 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank49 | Rating / score1,219.67 | Votes1,452 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank49 | Rating / score1,199.85 | Votes1,452 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank50 | Rating / score1,445.11 | Votes515 | ObservationsN/A | Result date |
GPT-5.3 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.75 input, $14 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $1.75 input, $14 output per 1M via Opper
- Tracked offerings
- 5
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOpenAI | Provider model IDgpt-5.3-chat-latest | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context128K | Updated |
| ProviderOpper | Provider model IDopenai/gpt-5.3-chat-latest | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context128K | Updated |
| ProviderMerge Gateway | Provider model IDopenai/gpt-5.3-chat-latest | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context128K | Updated |
| ProviderZenMux | Provider model IDopenai/gpt-5.3-chat | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context128K | Updated |
| ProviderAbacus | Provider model IDgpt-5.3-chat-latest | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-5.3 Runtime Performance
Provider-specific output speed and catalog latency for GPT-5.3 Chat. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed100.00 tok/s | Catalog Latency2.00 s | Max Input128K | Max Output16.4K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-5.3 Specifications
Technical details for the model's default version.
- Version
- GPT-5.3 Chat
- Released
- Mar 4, 2026
- Knowledge cutoff
- Aug 31, 2025
- Parameters
- N/A
- Context window
- 128K
- Max output
- 16.4K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-5.3 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 |
|---|
| VersionGPT-5.3 Chat | Released | LLMBoard41.12 | ParametersN/A | Context128K | Max output16.4K | Open weightsNo | LicenseProprietary |
Models similar to GPT-5.3
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-5-Mini
OpenAI
OP
GPT-OSS-120B
OpenAI
OP
GPT-5-Codex
OpenAI
OP
o4 mini
OpenAI
OP
GPT-OSS-20B
OpenAI
OP
o1
OpenAI
What is GPT-5.3?
Key information about GPT-5.3 and its available data.
3 Chat is OpenAI's instant model used in ChatGPT, with medium speed and support for streaming, function calling, and structured outputs.
Data as of 2026-09-08.
FAQ
Common questions about GPT-5.3.
When was GPT-5.3 released?
GPT-5.3's default version was released on Mar 4, 2026.
How much does GPT-5.3 cost?
GPT-5.3's official API price is $1.75 per million input tokens and $14 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $1.75 input and $14 output via Opper.
Who created GPT-5.3?
GPT-5.3 was created by OpenAI.
What is the context window for GPT-5.3?
The default version has a 128K token context window.
Is GPT-5.3 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-5.3?
5 provider offerings are linked to the default version.