GPT-5.2 by OpenAI demonstrates top-tier general intelligence, excellent coding ability, outstanding mathematical reasoning. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
General Benchmarks
Massive Multitask Language Understanding professional benchmark
HuggingFace LeaderboardCoding Benchmarks
Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Math Benchmarks
Reasoning Benchmarks
Multi-turn service agent making tool calls under strict policy constraints
OpenRouter (measured)Speed Benchmarks
Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 31 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 4 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| QiHang | $0.25 | $2 | — | 400K | — |
| UnoRouter | $1.05 | $8.4 | — | 400K | — |
| SAP AI Core | $1.25 | $9.44 | $0.12 | 400K | — |
| Jiekou.AI | $1.575 | $12.6 | — | 400K | — |
| Poe | $1.6 | $13 | $0.16 | 400K | — |
| 302.AI | $1.75 | $14 | — | 400K | — |
| Abacus | $1.75 | $14 | $0.175 | 400K | — |
| AIHubMix | $1.75 | $14 | $0.175 | 400K | — |
| Azure | $1.75 | $14 | $0.125 | 400K | Supported |
| Azure Cognitive Services | $1.75 | $14 | $0.125 | 400K | — |
| Databricks | $1.75 | $14 | $0.175 | 400K | — |
| DevPass (LLM Gateway) | $1.75 | $14 | $0.175 | 400K | — |
| Eden AI | $1.75 | $14 | $0.175 | 400K | — |
| Impossibl | $1.75 | $14 | $0.175 | 400K | — |
| Kilo Gateway | $1.75 | $14 | $0.175 | 400K | — |
| LLM Gateway | $1.75 | $14 | $0.175 | 400K | — |
| Merge Gateway | $1.75 | $14 | $0.175 | 400K | — |
| NanoGPT | $1.75 | $14 | $0.175 | 400K | — |
| NEAR AI Cloud | $1.75 | $14 | $0.175 | 400K | — |
| Neon | $1.75 | $14 | $0.175 | 400K | — |
| Ofox | $1.75 | $14 | $0.18 | 400K | — |
| OpenAI | $1.75 | $14 | $0.175 | 400K | Supported |
| OpenCode Zen | $1.75 | $14 | $0.175 | 400K | — |
| OpenRouter | $1.75 | $14 | $0.175 | 400K | Supported |
| OrcaRouter | $1.75 | $14 | $0.175 | 400K | — |
| Perplexity Agent | $1.75 | $14 | $0.175 | 400K | — |
| Vercel AI Gateway | $1.75 | $14 | $0.175 | 400K | Supported |
| ZenMux | $1.75 | $14 | $0.17 | 400K | — |
| Venice AI | $2.19 | $17.5 | $0.219 | 256K | — |
| AnyAPI | — | — | — | 400K | — |
| Snowflake Cortex | — | — | — | 400K | — |
GPT-5.2 — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare GPT-5.2 With
GPT-5.2 — Frequently Asked Questions
How intelligent is GPT-5.2?
GPT-5.2 scores 1475 on the Chatbot Arena ELO rating, making it one of the top-ranked AI model. This score is based on blind head-to-head human preference voting.
How much does GPT-5.2 cost?
GPT-5.2 costs $1.8 per 1M input tokens and $14.0 per 1M output tokens. This is mid-range pricing for its capability level.
How fast is GPT-5.2?
GPT-5.2 generates output at 90 tokens per second, which is moderate compared to other models. The time to first token is 380 ms.
How good is GPT-5.2 at coding?
GPT-5.2 achieves 80.0% on SWE-bench Verified, demonstrating excellent real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.
How good is GPT-5.2 at math and reasoning?
GPT-5.2 scores 97.0% on the MATH benchmark (competition-level mathematics). It also achieves 87.9% on GPQA Diamond, a graduate-level science reasoning benchmark.
What is the context window of GPT-5.2?
GPT-5.2 has a context window of 400K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created GPT-5.2?
GPT-5.2 was created by OpenAI. It is classified as a flagship model in our catalogue.
Is GPT-5.2 open source?
No, GPT-5.2 is a proprietary model. It is available through OpenAI's API and compatible providers.