GPT-5.2 (Non-reasoning)
Intelligence
33.6
#132/523
Coding
34.7
#97/429
Math
51
#138/265
Speed
70 tok/s
TTFT: 545.00s
Pricing
$1.75 / $14.00
per 1M tokens (in/out)
GPT-5.2 (Non-reasoning) is OpenAI’s latest model designed for various applications in natural language processing. It processes at 69.896 tokens per second and is priced at $1.75 per million input tokens and $14 per million output tokens, targeting professional users.
When to Use GPT-5.2 (Non-reasoning)
✓ Best For
- Text generation and completion
- Code generation and assistance
- Mathematical problem-solving
✗ Not Ideal For
- Complex reasoning tasks
- High-speed real-time applications
How GPT-5.2 (Non-reasoning) Compares
Intelligence Index · Higher is better
TencentInclusionAIOpenAIGoogleByteDance Seed
Benchmark Profile
Coding Index
KimiAlibabaOpenAIStepFunDeepSeek
Output Speed · tok/s
AlibabaZ AIOpenAIMistral
Math Index
AlibabaOpenAILG AI ResearchNVIDIA
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (13)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 33.6 | |
| Coding Index | 34.7 | |
| Math Index | 51 | |
| MMLU-Pro | 814% | |
| GPQA | 712% | |
| LiveCodeBench | 669% | |
| HLE | 73% | |
| SciCode | 40.4% | |
| IFBench | 47.4% | |
| LCR | 38% | |
| TerminalBench Hard | 31.8% | |
| Tau2 | 46.5% | |
| AIME 2025 | 51% |
Data: Artificial Analysis · Updated: March 28, 2026
Frequently Asked Questions (15)
When was GPT-5.2 (Non-reasoning) released?
GPT-5.2 (Non-reasoning) was released on December 11, 2025.
Who created GPT-5.2 (Non-reasoning)?
GPT-5.2 (Non-reasoning) was created by OpenAI.
How intelligent is GPT-5.2 (Non-reasoning)?
GPT-5.2 (Non-reasoning) scores 34 on the Artificial Analysis Intelligence Index, placing it well above average among other non-reasoning models in a similar price tier (median: 22).
How fast is GPT-5.2 (Non-reasoning)?
GPT-5.2 (Non-reasoning) generates output at 64.3 tokens per second (based on OpenAI's API), which is above average compared to other non-reasoning models in a similar price tier (median: 57.5 t/s).
What is the latency of GPT-5.2 (Non-reasoning)?
GPT-5.2 (Non-reasoning) has a time to first token (TTFT) of 1.03s (based on OpenAI's API), which is very competitive compared to other non-reasoning models in a similar price tier (median: 1.51s).
How much does GPT-5.2 (Non-reasoning) cost?
GPT-5.2 (Non-reasoning) costs $1.75 per 1M input tokens (better than average, median: $2.00) and $14.00 per 1M output tokens (somewhat higher than average, median: $8.00), based on OpenAI's API.
What is GPT-5.2 (Non-reasoning) API pricing?
GPT-5.2 (Non-reasoning) costs $1.75 per 1M input tokens and $14.00 per 1M output tokens (based on OpenAI's API). For a blended rate (3:1 input to output ratio), this is $4.81 per 1M tokens. Pricing may vary by provider.
How verbose is GPT-5.2 (Non-reasoning)?
When evaluated on the Intelligence Index, GPT-5.2 (Non-reasoning) generated 3.8M output tokens, which is better than average compared to other non-reasoning models in a similar price tier (median: 3.9M).
Is GPT-5.2 (Non-reasoning) a reasoning model?
No, GPT-5.2 (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does GPT-5.2 (Non-reasoning) support?
GPT-5.2 (Non-reasoning) supports text and image input.
What output modalities does GPT-5.2 (Non-reasoning) support?
GPT-5.2 (Non-reasoning) supports text output.
Can GPT-5.2 (Non-reasoning) process images?
Yes, GPT-5.2 (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.
Is GPT-5.2 (Non-reasoning) multimodal?
Yes, GPT-5.2 (Non-reasoning) is multimodal. It can process text and image input and generate text output.
What is the context window of GPT-5.2 (Non-reasoning)?
GPT-5.2 (Non-reasoning) has a context window of 400k tokens. This determines how much text and conversation history the model can process in a single request.
Is GPT-5.2 (Non-reasoning) open source?
No, GPT-5.2 (Non-reasoning) is proprietary. The model weights are not publicly available.
