GPT-4.1 by OpenAI demonstrates strong general intelligence, solid coding performance. 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
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 27 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 |
|---|---|---|---|---|---|
| Poe | $1.8 | $7.2 | $0.45 | 1.0M | — |
| 302.AI | $2 | $8 | — | 1.0M | — |
| Abacus | $2 | $8 | $0.5 | 1.0M | — |
| Azure | $2 | $8 | $0.5 | 1.0M | Supported |
| Azure Cognitive Services | $2 | $8 | $0.5 | 1.0M | — |
| Cloudflare AI Gateway | $2 | $8 | $0.5 | 1.0M | — |
| DevPass (LLM Gateway) | $2 | $8 | $0.5 | 1.0M | — |
| Eden AI | $2 | $8 | $0.5 | 1.0M | — |
| FastRouter | $2 | $8 | $0.5 | 1.0M | — |
| Impossibl | $2 | $8 | $0.5 | 1.0M | — |
| Kilo Gateway | $2 | $8 | $0.5 | 1.0M | — |
| LLM Gateway | $2 | $8 | $0.5 | 1.0M | — |
| Merge Gateway | $2 | $8 | $0.5 | 1.0M | — |
| NanoGPT | $2 | $8 | $0.5 | 1.0M | — |
| NEAR AI Cloud | $2 | $8 | $0.5 | 1.0M | — |
| Ofox | $2 | $8 | $0.5 | 1.0M | — |
| OpenAI | $2 | $8 | $0.5 | 1.0M | Supported |
| OpenRouter | $2 | $8 | $0.5 | 1.0M | Supported |
| OrcaRouter | $2 | $8 | $0.5 | 1.0M | — |
| Pioneer | $2 | $8 | $1 | 1.0M | — |
| SAP AI Core | $2 | $8 | $0.32 | 1.0M | — |
| Vercel AI Gateway | $2 | $8 | $0.5 | 1.0M | Supported |
| Cortecs | $2.192 | $8.769 | $0.546 | 1.0M | — |
| Requesty | $2.2 | $8.8 | $0.55 | 1.0M | — |
| AnyAPI | — | — | — | 1.0M | — |
| Model Oracle AI | — | — | — | 1.0M | — |
| Snowflake Cortex | — | — | — | 1.0M | — |
GPT-4.1 — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare GPT-4.1 With
GPT-4.1 — Frequently Asked Questions
How intelligent is GPT-4.1?
GPT-4.1 scores 1340 on the Chatbot Arena ELO rating, making it a mid-tier AI model. This score is based on blind head-to-head human preference voting.
How much does GPT-4.1 cost?
GPT-4.1 costs $2.0 per 1M input tokens and $8.0 per 1M output tokens. This is mid-range pricing for its capability level.
How fast is GPT-4.1?
GPT-4.1 generates output at 70 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 450 ms.
How good is GPT-4.1 at coding?
GPT-4.1 achieves 50.0% on SWE-bench Verified, demonstrating strong real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.
How good is GPT-4.1 at math and reasoning?
GPT-4.1 scores 83.0% on the MATH benchmark (competition-level mathematics). It also achieves 64.9% on GPQA Diamond, a graduate-level science reasoning benchmark.
What is the context window of GPT-4.1?
GPT-4.1 has a context window of 1.0M tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created GPT-4.1?
GPT-4.1 was created by OpenAI. It is classified as a mid model in our catalogue.
Is GPT-4.1 open source?
No, GPT-4.1 is a proprietary model. It is available through OpenAI's API and compatible providers.