Model Comparison

GPT-4.1 vs GPT-4.5Which is better in 2026?

GPT-4.5 shows notably better performance in the majority of benchmarks. GPT-4.1 is 26.8x cheaper per token.

Verdict: GPT-4.1 vs GPT-4.5 — which is better?

GPT-4.1 (by OpenAI) and GPT-4.5 (by OpenAI) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

GPT-4.1 outperforms in 7 benchmarks (Aider-Polyglot Edit, AIME 2024, CharXiv-R, ComplexFuncBench, MMMLU, OpenAI-MRCR: 2 needle 128k, SWE-Bench Verified), while GPT-4.5 is better at 13 benchmarks (CharXiv-D, COLLIE, GPQA, Graphwalks BFS <128k, Graphwalks parents <128k, IFEval, Internal API instruction following (hard), MathVista, MMLU, MMMU, Multi-Challenge, TAU-bench Airline, TAU-bench Retail). GPT-4.5 shows notably better performance in the majority of benchmarks.

On price, GPT-4.1 is roughly 26.8x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

GPT-4.1 also accepts a larger context window (1,047,576 input tokens), making it the stronger choice for long documents and large codebases.

Choose GPT-4.1 if…

  • cost matters — it's about 26.8x cheaper per token
  • you process long inputs — it offers a 1,047,576 token context window
  • you want the most recent training data — it shipped Apr 2025

Choose GPT-4.5 if…

  • you want the strongest raw capability — it leads on 14 of 21 shared benchmarks

Performance Benchmarks

Comparative analysis across standard metrics

21 benchmarks

GPT-4.1 outperforms in 7 benchmarks (Aider-Polyglot Edit, AIME 2024, CharXiv-R, ComplexFuncBench, MMMLU, OpenAI-MRCR: 2 needle 128k, SWE-Bench Verified), while GPT-4.5 is better at 13 benchmarks (CharXiv-D, COLLIE, GPQA, Graphwalks BFS <128k, Graphwalks parents <128k, IFEval, Internal API instruction following (hard), MathVista, MMLU, MMMU, Multi-Challenge, TAU-bench Airline, TAU-bench Retail).

GPT-4.5 shows notably better performance in the majority of benchmarks.

Wed Jul 15 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

GPT-4.1 costs less

For input processing, GPT-4.1 ($2.00/1M tokens) is 37.5x cheaper than GPT-4.5 ($75.00/1M tokens).

For output processing, GPT-4.1 ($8.00/1M tokens) is 18.8x cheaper than GPT-4.5 ($150.00/1M tokens).

In conclusion, GPT-4.5 is more expensive than GPT-4.1.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Wed Jul 15 2026 • llm-stats.com
OpenAI
GPT-4.1
Input tokens$2.00
Output tokens$8.00
Best providerOpenAI
OpenAI
GPT-4.5
Input tokens$75.00
Output tokens$150.00
Best providerOpenAI
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

GPT-4.1 accepts 1,047,576 input tokens compared to GPT-4.5's 128,000 tokens. GPT-4.1 can generate longer responses up to 32,768 tokens, while GPT-4.5 is limited to 4,096 tokens.

OpenAI
GPT-4.1
Input1,047,576 tokens
Output32,768 tokens
OpenAI
GPT-4.5
Input128,000 tokens
Output4,096 tokens
Wed Jul 15 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both GPT-4.1 and GPT-4.5 support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

GPT-4.1

Text
Images
Audio
Video

GPT-4.5

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

GPT-4.1

Proprietary

Closed source

GPT-4.5

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-4.1 was released on 2025-04-14, while GPT-4.5 was released on 2025-02-27.

GPT-4.1 is 2 months newer than GPT-4.5.

GPT-4.1

Apr 14, 2025

1.2 years ago

1mo newer
GPT-4.5

Feb 27, 2025

1.4 years ago

Knowledge Cutoff

When training data ends

GPT-4.1 has a documented knowledge cutoff of 2024-06-01, while GPT-4.5's cutoff date is not specified.

We can confirm GPT-4.1's training data extends to 2024-06-01, but cannot make a direct comparison without GPT-4.5's cutoff date.

GPT-4.1

Jun 2024

GPT-4.5

—

Provider Availability

GPT-4.1 is available from OpenAI. GPT-4.5 is available from OpenAI.

GPT-4.1

openai logo
OpenAI
Input Price:Input: $2.00/1MOutput Price:Output: $8.00/1M

GPT-4.5

openai logo
OpenAI
Input Price:Input: $75.00/1MOutput Price:Output: $150.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

OpenAI
Larger context window (1,047,576 tokens)
Less expensive input tokens
Less expensive output tokens
Higher Aider-Polyglot Edit score (52.9% vs 44.9%)
Higher AIME 2024 score (48.1% vs 36.7%)
Higher CharXiv-R score (56.7% vs 55.4%)
Higher ComplexFuncBench score (65.5% vs 63.0%)
Higher MMMLU score (87.3% vs 85.1%)
Higher OpenAI-MRCR: 2 needle 128k score (57.2% vs 38.5%)
Higher SWE-Bench Verified score (54.6% vs 38.0%)
OpenAI
Higher CharXiv-D score (90.0% vs 87.9%)
Higher COLLIE score (72.3% vs 65.8%)
Higher GPQA score (69.5% vs 66.3%)
Higher Graphwalks BFS <128k score (72.3% vs 61.7%)
Higher Graphwalks parents <128k score (72.6% vs 58.0%)
Higher IFEval score (88.2% vs 87.4%)
Higher Internal API instruction following (hard) score (54.0% vs 49.1%)
Higher MathVista score (72.3% vs 72.2%)
Higher MMLU score (90.8% vs 90.2%)
Higher MMMU score (75.2% vs 74.8%)
Higher Multi-Challenge score (43.8% vs 38.3%)
Higher TAU-bench Airline score (50.0% vs 49.4%)
Higher TAU-bench Retail score (68.4% vs 68.0%)
OpenAIGPT-4.1
OpenAIGPT-4.5
Compare in Playground

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against GPT-4.1 and GPT-4.5 side-by-side, then vote on the output you prefer.

GPT-4.1
✓ Preferred
GPT-4.5
Open in Playground
AI Model Comparison Table
Feature
OpenAI
GPT-4.1
OpenAI
GPT-4.5

FAQ

Common questions about GPT-4.1 vs GPT-4.5.

Which is better, GPT-4.1 or GPT-4.5?

GPT-4.5 shows notably better performance in the majority of benchmarks. GPT-4.1 is made by OpenAI and GPT-4.5 is made by OpenAI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does GPT-4.1 compare to GPT-4.5 in benchmarks?

GPT-4.1 scores MMLU: 90.2%, CharXiv-D: 87.9%, IFEval: 87.4%, MMMLU: 87.3%, MMMU: 74.8%. GPT-4.5 scores GSM8k: 97.0%, MMLU: 90.8%, CharXiv-D: 90.0%, IFEval: 88.2%, HumanEval: 88.0%.

Is GPT-4.1 cheaper than GPT-4.5?

GPT-4.1 is 37.5x cheaper for input tokens. GPT-4.1 costs $2.00/M input and $8.00/M output via openai. GPT-4.5 costs $75.00/M input and $150.00/M output via openai.

What are the context window sizes for GPT-4.1 and GPT-4.5?

GPT-4.1 supports 1.0M tokens and GPT-4.5 supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between GPT-4.1 and GPT-4.5?

Key differences include context window (1.0M vs 128K), input pricing ($2.00 vs $75.00/M). See the full comparison above for benchmark-by-benchmark results.

Related comparisons