Model Comparison

GPT-5 mini vs Claude Sonnet 4

GPT-5 mini significantly outperforms across most benchmarks. GPT-5 mini is 8.7x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

2 benchmarks

GPT-5 mini outperforms in 2 benchmarks (AIME 2025, GPQA), while Claude Sonnet 4 is better at 0 benchmarks.

GPT-5 mini significantly outperforms across most benchmarks.

Thu May 14 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

GPT-5 mini costs less

For input processing, GPT-5 mini ($0.25/1M tokens) is 12.0x cheaper than Claude Sonnet 4 ($3.00/1M tokens).

For output processing, GPT-5 mini ($2.00/1M tokens) is 7.5x cheaper than Claude Sonnet 4 ($15.00/1M tokens).

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

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

Lowest available price from all providers
Thu May 14 2026 • llm-stats.com
OpenAI
GPT-5 mini
Input tokens$0.25
Output tokens$2.00
Best providerOpenAI
Anthropic
Claude Sonnet 4
Input tokens$3.00
Output tokens$15.00
Best providerAnthropic
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

GPT-5 mini accepts 400,000 input tokens compared to Claude Sonnet 4's 200,000 tokens. GPT-5 mini can generate longer responses up to 128,000 tokens, while Claude Sonnet 4 is limited to 64,000 tokens.

OpenAI
GPT-5 mini
Input400,000 tokens
Output128,000 tokens
Anthropic
Claude Sonnet 4
Input200,000 tokens
Output64,000 tokens
Thu May 14 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both GPT-5 mini and Claude Sonnet 4 support multimodal inputs.

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

GPT-5 mini

Text
Images
Audio
Video

Claude Sonnet 4

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-5 mini

Proprietary

Closed source

Claude Sonnet 4

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-5 mini was released on 2025-08-07, while Claude Sonnet 4 was released on 2025-05-22.

GPT-5 mini is 3 months newer than Claude Sonnet 4.

GPT-5 mini

Aug 7, 2025

9 months ago

2mo newer
Claude Sonnet 4

May 22, 2025

11 months ago

Knowledge Cutoff

When training data ends

GPT-5 mini has a documented knowledge cutoff of 2024-05-30, while Claude Sonnet 4's cutoff date is not specified.

We can confirm GPT-5 mini's training data extends to 2024-05-30, but cannot make a direct comparison without Claude Sonnet 4's cutoff date.

GPT-5 mini

May 2024

Claude Sonnet 4

—

Provider Availability

GPT-5 mini is available from OpenAI. Claude Sonnet 4 is available from Anthropic, Bedrock, Google.

GPT-5 mini

openai logo
OpenAI
Input Price:Input: $0.25/1MOutput Price:Output: $2.00/1M

Claude Sonnet 4

anthropic logo
Anthropic
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
bedrock logo
AWS Bedrock
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
google logo
Google
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

OpenAI
Larger context window (400,000 tokens)
Less expensive input tokens
Less expensive output tokens
Higher AIME 2025 score (91.1% vs 70.5%)
Higher GPQA score (82.3% vs 75.4%)
Anthropic

No standout differentiators in the data we have for this pair.

OpenAIGPT-5 mini
AnthropicClaude Sonnet 4
Compare in Playground

Detailed Comparison

AI Model Comparison Table
Feature
OpenAI
GPT-5 mini
Anthropic
Claude Sonnet 4

FAQ

Common questions about GPT-5 mini vs Claude Sonnet 4.

Which is better, GPT-5 mini or Claude Sonnet 4?

GPT-5 mini significantly outperforms across most benchmarks. GPT-5 mini is made by OpenAI and Claude Sonnet 4 is made by Anthropic. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does GPT-5 mini compare to Claude Sonnet 4 in benchmarks?

GPT-5 mini scores AIME 2025: 91.1%, HMMT 2025: 87.8%, GPQA: 82.3%, FrontierMath: 22.1%, Humanity's Last Exam: 16.7%. Claude Sonnet 4 scores MMMLU: 86.5%, TAU-bench Retail: 80.5%, GPQA: 75.4%, MMMU: 74.4%, SWE-Bench Verified: 72.7%.

Is GPT-5 mini cheaper than Claude Sonnet 4?

GPT-5 mini is 12.0x cheaper for input tokens. GPT-5 mini costs $0.25/M input and $2.00/M output via openai. Claude Sonnet 4 costs $3.00/M input and $15.00/M output via anthropic.

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

GPT-5 mini supports 400K tokens and Claude Sonnet 4 supports 200K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between GPT-5 mini and Claude Sonnet 4?

Key differences include context window (400K vs 200K), input pricing ($0.25 vs $3.00/M). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-5 mini and Claude Sonnet 4?

GPT-5 mini is developed by OpenAI and Claude Sonnet 4 is developed by Anthropic.