GPT-5.1 Codex by OpenAI demonstrates strong general intelligence, excellent coding ability. 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 LeaderboardHuman preference ELO from blind head-to-head votes
LMSYS / HuggingFaceCoding 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
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 18 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 3 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| OpenCode Zen | $1.07 | $8.5 | $0.107 | 400K | — |
| Poe | $1.1 | $9 | $0.11 | 400K | — |
| Jiekou.AI | $1.125 | $9 | — | 400K | — |
| Abacus | $1.25 | $10 | $0.125 | 400K | — |
| AIHubMix | $1.25 | $10 | $0.125 | 400K | — |
| Azure | $1.25 | $10 | $0.125 | 400K | Supported |
| Azure Cognitive Services | $1.25 | $10 | $0.125 | 400K | — |
| DevPass (LLM Gateway) | $1.25 | $10 | $0.125 | 400K | — |
| Eden AI | $1.25 | $10 | $0.125 | 272K | — |
| Impossibl | $1.25 | $10 | $0.125 | 400K | — |
| Kilo Gateway | $1.25 | $10 | $0.13 | 400K | — |
| LLM Gateway | $1.25 | $10 | — | 400K | — |
| NanoGPT | $1.25 | $10 | $0.125 | 400K | — |
| OpenRouter | $1.25 | $10 | $0.13 | 400K | Supported |
| OrcaRouter | $1.25 | $10 | $0.125 | 400K | — |
| Vercel AI Gateway | $1.25 | $10 | $0.13 | 400K | Supported |
| Vivgrid | $1.25 | $10 | $0.125 | 400K | — |
| ZenMux | $1.25 | $10 | $0.12 | 400K | — |
GPT-5.1 Codex — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare GPT-5.1 Codex With
GPT-5.1 Codex — Frequently Asked Questions
How intelligent is GPT-5.1 Codex?
GPT-5.1 Codex scores 1395 on the Chatbot Arena ELO rating, making it a high-performing AI model. This score is based on blind head-to-head human preference voting.
How much does GPT-5.1 Codex cost?
GPT-5.1 Codex costs $1.3 per 1M input tokens and $10.0 per 1M output tokens. This is mid-range pricing for its capability level.
How fast is GPT-5.1 Codex?
GPT-5.1 Codex generates output at 85 tokens per second, which is moderate compared to other models. The time to first token is 400 ms.
How good is GPT-5.1 Codex at coding?
GPT-5.1 Codex achieves 78.0% 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-5.1 Codex at math and reasoning?
GPT-5.1 Codex scores 85.0% on the MATH benchmark (competition-level mathematics). It also achieves 65.0% on GPQA Diamond, a graduate-level science reasoning benchmark.
What is the context window of GPT-5.1 Codex?
GPT-5.1 Codex 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-5.1 Codex?
GPT-5.1 Codex was created by OpenAI. It is classified as a flagship model in our catalogue.
Is GPT-5.1 Codex open source?
No, GPT-5.1 Codex is a proprietary model. It is available through OpenAI's API and compatible providers.