GPT-5 High vs Claude Haiku 4.5 Comparison

Comparing GPT-5 High and Claude Haiku 4.5 across benchmarks, pricing, and capabilities.

Performance Benchmarks

Comparative analysis across standard metrics

2 benchmarks

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

GPT-5 High significantly outperforms across most benchmarks.

Tue Mar 17 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Claude Haiku 4.5 costs less

For input processing, GPT-5 High ($1.25/1M tokens) is 1.3x more expensive than Claude Haiku 4.5 ($1.00/1M tokens).

For output processing, GPT-5 High ($10.00/1M tokens) is 2.0x more expensive than Claude Haiku 4.5 ($5.00/1M tokens).

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

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

Lowest available price from all providers
Tue Mar 17 2026 • llm-stats.com
OpenAI
GPT-5 High
Input tokens$1.25
Output tokens$10.00
Best providerOpenAI
Anthropic
Claude Haiku 4.5
Input tokens$1.00
Output tokens$5.00
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 Haiku 4.5's 200,000 tokens. GPT-5 High can generate longer responses up to 128,000 tokens, while Claude Haiku 4.5 is limited to 64,000 tokens.

OpenAI
GPT-5 High
Input400,000 tokens
Output128,000 tokens
Anthropic
Claude Haiku 4.5
Input200,000 tokens
Output64,000 tokens
Tue Mar 17 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both GPT-5 High and Claude Haiku 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 Haiku 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 Haiku 4.5

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-5 High was released on 2025-08-07, while Claude Haiku 4.5 was released on 2025-10-15.

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

GPT-5 High

Aug 7, 2025

7 months ago

Claude Haiku 4.5

Oct 15, 2025

5 months ago

2mo newer

Knowledge Cutoff

When training data ends

GPT-5 High has a knowledge cutoff of 2024-09-30, while Claude Haiku 4.5 has a cutoff of 2025-02-01.

Claude Haiku 4.5 has more recent training data (up to 2025-02-01), making it potentially better informed about events through that date compared to GPT-5 High (2024-09-30).

GPT-5 High

Sep 2024

Claude Haiku 4.5

Feb 2025

5 mo newer

Provider Availability

GPT-5 High is available from OpenAI. Claude Haiku 4.5 is available from Anthropic. The availability of providers can affect quality of the model and reliability.

GPT-5 High

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

Claude Haiku 4.5

anthropic logo
Anthropic
Input Price:Input: $1.00/1MOutput Price:Output: $5.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Key Takeaways

Larger context window (400,000 tokens)
Higher AIME 2025 score (94.6% vs 80.7%)
Higher GPQA score (87.3% vs 73.0%)
Less expensive input tokens
Less expensive output tokens

Detailed Comparison

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