Model Comparison

Comprehensive side-by-side analysis of model capabilities and performance

Anthropic

Claude Sonnet 4.5

Anthropic

Claude Sonnet 4.5 is a multimodal language model developed by Anthropic. It achieves strong performance with an average score of 78.0% across 10 benchmarks. It excels particularly in Tau2 Telecom (98.0%), MMMLU (89.1%), AIME 2025 (87.0%). It supports a 264K token context window for handling large documents. The model is available through 2 API providers. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2025, it represents Anthropic's latest advancement in AI technology.

OpenAI

GPT-3.5 Turbo

OpenAI

GPT-3.5 Turbo is a language model developed by OpenAI. The model shows competitive results across 8 benchmarks. Notable strengths include DROP (70.2%), MMLU (69.8%), HumanEval (68.0%). The model is available through 2 API providers.

OpenAI

GPT-3.5 Turbo

OpenAI

2023-03-21

Anthropic

Claude Sonnet 4.5

Anthropic

2025-09-29

2 years newer

Pricing Comparison

Cost per million tokens (USD)

Anthropic

Claude Sonnet 4.5

Input:$3.00
Output:$15.00
OpenAI

GPT-3.5 Turbo

$16.00 cheaper
Input:$0.50
Output:$1.50

Performance Metrics

Context window and performance specifications

Anthropic

Claude Sonnet 4.5

Larger context
Max Context:264.0K
OpenAI

GPT-3.5 Turbo

Max Context:20.5K

Average performance across 17 common benchmarks

Anthropic

Claude Sonnet 4.5

+26.0%
Average Score:45.9%
OpenAI

GPT-3.5 Turbo

Average Score:19.9%

Performance comparison across key benchmark categories

Anthropic

Claude Sonnet 4.5

math
+53.9%
87.0%
general
+21.0%
78.0%
code
50.0%
OpenAI

GPT-3.5 Turbo

math
33.1%
general
56.9%
code
+18.0%
68.0%
Knowledge Cutoff
Training data recency comparison

GPT-3.5 Turbo

2021-09-30

Claude Sonnet 4.5

2025-01-31

More recent knowledge cutoff means awareness of newer technologies and frameworks

Provider Availability & Performance

Available providers and their performance metrics

Anthropic

Claude Sonnet 4.5

2 providers

Anthropic

Throughput: 42 tok/s
Latency: 0.4ms

ZeroEval

Throughput: 42 tok/s
Latency: 0.4ms
OpenAI

GPT-3.5 Turbo

2 providers

Azure

Throughput: 90 tok/s
Latency: 0.8ms

OpenAI

Throughput: 100 tok/s
Latency: 0.5ms
Anthropic

Claude Sonnet 4.5

+26.0%
Avg Score:45.9%
Providers:2
OpenAI

GPT-3.5 Turbo

Avg Score:19.9%
Providers:2