The AI arena is free today

Open Superagent

GPT-4 vs GPT-5

GPT-5 leads the LLM Stats Score 34.3 to 3.3. GPT-5 is 10.9x cheaper per token.

OpenAI · OpenAI · Updated for 2026

Which is better?

GPT-5 leads the overall LLM Stats Score 34.3 to 3.3, ranking #83 overall.

In the 4 individual benchmarks reported for both models, GPT-5 wins 4; this is a narrower head-to-head signal than the composite indexes.

On price, GPT-5 is roughly 10.9x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

GPT-5 also accepts a larger context window (400,000 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose GPT-4

  • you want predictable pricing at $30.00/M input and $60.00/M output

Choose GPT-5

  • overall performance matters — it scores 34.3 and ranks #83 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 4 of 4 exact shared results
  • cost matters — it's about 10.9x cheaper per token
  • you process long inputs — it offers a 400,000 token context window
  • you want the most recent training data — it shipped Aug 2025

At a glance

The differences that matter most.

Core performance indexes
3.3
#293
34.3
#83
3.4
#285
34.7
#81
-5.1
#246
26.6
#55
Cost, coverage & limits
Benchmark wins
0 of 4
4 of 4
Input price
$30.00 / M
$1.25 / M
Output price
$60.00 / M
$10.00 / M
Context window
32,768
400,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
GPT-4
GPT-5
8.8#249
31.4#62
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

12 reported for GPT-4 · 34 for GPT-5

4 shared

GPT-4 outperforms in 0 benchmarks, while GPT-5 is better at 4 benchmarks (GPQA, HumanEval, MATH, MMLU).

GPT-5 significantly outperforms across most benchmarks.

Mon Aug 31 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

GPT-5 costs less

For input processing, GPT-4 ($30.00/1M tokens) is 24.0x more expensive than GPT-5 ($1.25/1M tokens).

For output processing, GPT-4 ($60.00/1M tokens) is 6.0x more expensive than GPT-5 ($10.00/1M tokens).

In conclusion, GPT-4 is more expensive than GPT-5.*

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

Lowest available price from all providers
Mon Aug 31 2026 • llm-stats.com
OpenAI
GPT-4
Input tokens$30.00
Output tokens$60.00
Best providerAzure
OpenAI
GPT-5
Input tokens$1.25
Output tokens$10.00
Best providerOpenAI
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

GPT-5 accepts 400,000 input tokens compared to GPT-4's 32,768 tokens. GPT-5 can generate longer responses up to 128,000 tokens, while GPT-4 is limited to 32,768 tokens.

OpenAI
GPT-4
Input32,768 tokens
Output32,768 tokens
OpenAI
GPT-5
Input400,000 tokens
Output128,000 tokens
Mon Aug 31 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both GPT-4 and GPT-5 support multimodal inputs.

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

GPT-4

Text
Images
Audio
Video

GPT-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

Proprietary

Closed source

GPT-5

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-4 was released on 2023-06-13, while GPT-5 was released on 2025-08-07.

GPT-5 is 26 months newer than GPT-4.

GPT-4

Jun 13, 2023

3.2 years ago

GPT-5

Aug 7, 2025

1.1 years ago

2.2yr newer

Knowledge Cutoff

When training data ends

GPT-4 has a knowledge cutoff of 2022-12-31, while GPT-5 has a cutoff of 2024-09-30.

GPT-5 has more recent training data (up to 2024-09-30), making it potentially better informed about events through that date compared to GPT-4 (2022-12-31).

GPT-4

Dec 2022

GPT-5

Sep 2024

1.8 yr newer

Provider Availability

GPT-4 is available from Azure, OpenAI. GPT-5 is available from OpenAI.

GPT-4

azure logo
Azure
Input Price:Input: $30.00/1MOutput Price:Output: $60.00/1M
openai logo
OpenAI
Input Price:Input: $30.00/1MOutput Price:Output: $60.00/1M

GPT-5

openai logo
OpenAI
Input Price:Input: $1.25/1MOutput Price:Output: $10.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against GPT-4 and GPT-5 side-by-side, then vote on the output you prefer.

GPT-4
✓ Preferred
GPT-5
Open in Playground

FAQ

Common questions about GPT-4 vs GPT-5.

Which is better, GPT-4 or GPT-5?

GPT-5 leads the LLM Stats Score 34.3 to 3.3. GPT-4 is made by OpenAI and GPT-5 is made by OpenAI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does GPT-4 compare to GPT-5 in benchmarks?

GPT-4 scores AI2 Reasoning Challenge (ARC): 96.3%, HellaSwag: 95.3%, Uniform Bar Exam: 90.0%, SAT Math: 89.0%, LSAT: 88.0%. GPT-5 scores SWE-Lancer (IC-Diamond subset): 100.0%, COLLIE: 99.0%, Tau2 Telecom: 96.7%, OpenAI-MRCR: 2 needle 128k: 95.2%, AIME 2025: 94.6%.

Is GPT-4 cheaper than GPT-5?

GPT-5 is 24.0x cheaper for input tokens. GPT-4 costs $30.00/M input and $60.00/M output via azure. GPT-5 costs $1.25/M input and $10.00/M output via openai.

What are the context window sizes for GPT-4 and GPT-5?

GPT-4 supports 33K tokens and GPT-5 supports 400K 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 and GPT-5?

Key differences include LLM Stats Score (3.3 vs 34.3), context window (33K vs 400K), input pricing ($30.00 vs $1.25/M). See the full comparison above for benchmark-by-benchmark results.