Model Comparison

GPT-5 High vs Claude Sonnet 4.5

GPT-5 High significantly outperforms across most benchmarks. GPT-5 High is 1.7x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

2 benchmarks

GPT-5 High outperforms in 2 benchmarks (AIME 2025, GPQA), while Claude Sonnet 4.5 is better at 0 benchmarks.

GPT-5 High significantly outperforms across most benchmarks.

Thu Apr 16 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

GPT-5 High costs less

For input processing, GPT-5 High ($1.25/1M tokens) is 2.4x cheaper than Claude Sonnet 4.5 ($3.00/1M tokens).

For output processing, GPT-5 High ($10.00/1M tokens) is 1.5x cheaper than Claude Sonnet 4.5 ($15.00/1M tokens).

In conclusion, Claude Sonnet 4.5 is more expensive than GPT-5 High.*

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

Lowest available price from all providers
Thu Apr 16 2026 • llm-stats.com
OpenAI
GPT-5 High
Input tokens$1.25
Output tokens$10.00
Best providerOpenAI
Anthropic
Claude Sonnet 4.5
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 High accepts 400,000 input tokens compared to Claude Sonnet 4.5's 200,000 tokens. GPT-5 High can generate longer responses up to 128,000 tokens, while Claude Sonnet 4.5 is limited to 64,000 tokens.

OpenAI
GPT-5 High
Input400,000 tokens
Output128,000 tokens
Anthropic
Claude Sonnet 4.5
Input200,000 tokens
Output64,000 tokens
Thu Apr 16 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both GPT-5 High and Claude Sonnet 4.5 support multimodal inputs.

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

GPT-5 High

Text
Images
Audio
Video

Claude Sonnet 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-5 High

Proprietary

Closed source

Claude Sonnet 4.5

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-5 High was released on 2025-08-07, while Claude Sonnet 4.5 was released on 2025-09-29.

Claude Sonnet 4.5 is 2 months newer than GPT-5 High.

GPT-5 High

Aug 7, 2025

8 months ago

Claude Sonnet 4.5

Sep 29, 2025

6 months ago

1mo newer

Knowledge Cutoff

When training data ends

GPT-5 High has a knowledge cutoff of 2024-09-30, while Claude Sonnet 4.5 has a cutoff of 2025-01-31.

Claude Sonnet 4.5 has more recent training data (up to 2025-01-31), making it potentially better informed about events through that date compared to GPT-5 High (2024-09-30).

GPT-5 High

Sep 2024

Claude Sonnet 4.5

Jan 2025

4 mo newer

Provider Availability

GPT-5 High is available from OpenAI. Claude Sonnet 4.5 is available from Anthropic.

GPT-5 High

openai logo
OpenAI
Input Price:Input: $1.25/1MOutput Price:Output: $10.00/1M

Claude Sonnet 4.5

anthropic logo
Anthropic
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 (94.6% vs 87.0%)
Higher GPQA score (87.3% vs 83.4%)
Anthropic

Detailed Comparison

AI Model Comparison Table
Feature
OpenAI
GPT-5 High
Anthropic
Claude Sonnet 4.5

FAQ

Common questions about GPT-5 High vs Claude Sonnet 4.5

GPT-5 High significantly outperforms across most benchmarks. GPT-5 High is made by OpenAI and Claude Sonnet 4.5 is made by Anthropic. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
GPT-5 High scores AIME 2025: 94.6%, GPQA: 87.3%. Claude Sonnet 4.5 scores MMMLU: 89.1%, AIME 2025: 87.0%, TAU-bench Retail: 86.2%, GPQA: 83.4%, MMMUval: 77.8%.
GPT-5 High is 2.4x cheaper for input tokens. GPT-5 High costs $1.25/M input and $10.00/M output via openai. Claude Sonnet 4.5 costs $3.00/M input and $15.00/M output via anthropic.
GPT-5 High supports 400K tokens and Claude Sonnet 4.5 supports 200K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (400K vs 200K), input pricing ($1.25 vs $3.00/M). See the full comparison above for benchmark-by-benchmark results.
GPT-5 High is developed by OpenAI and Claude Sonnet 4.5 is developed by Anthropic.