+
+
+
+
+
+
+
+
VS
VS
VS
VS
VS
VS
Claude 3.5 Sonnet vs GPT-4
Comprehensive side-by-side LLM comparison
Claude 3.5 Sonnet leads with 20.3% higher average benchmark score. Claude 3.5 Sonnet offers 334.5K more tokens in context window than GPT-4. Claude 3.5 Sonnet is $72.00 cheaper per million tokens. Overall, Claude 3.5 Sonnet is the stronger choice for coding tasks.
+
+
+
+
Anthropic
This upgraded version of Claude 3.5 Sonnet was released with significant improvements in coding and agentic tool use. Built to deliver enhanced performance in software engineering tasks, it brought substantial gains in reasoning and problem-solving while introducing the groundbreaking computer use capability in public beta, allowing it to interact with computer interfaces like a human.
+
+
+
+
OpenAI
GPT-4 was created as a large multimodal model capable of accepting image and text inputs while producing text outputs. Developed to exhibit human-level performance on various professional and academic benchmarks, it marked a significant advancement in reliability, creativity, and handling of nuanced instructions compared to its predecessors.
1 year newer
GPT-4
OpenAI
2023-06-13
Claude 3.5 Sonnet
Anthropic
2024-10-22
+
+
+
+
+
+
+
+
+
+
+
+
Pricing Comparison
Cost per million tokens (USD)
+
+
+
+
Claude 3.5 Sonnet
Input:$3.00
Output:$15.00($72.00 cheaper)
+
+
+
+
GPT-4
Input:$30.00
Output:$60.00
Performance Metrics
Context window and performance specifications
Average performance across 6 common benchmarks
+
+
+
+
Claude 3.5 Sonnet
Average Score:84.7%(+20.3%)
+
+
+
+
GPT-4
Average Score:64.4%
+
+
+
+
Knowledge Cutoff
Training data recency comparison
GPT-4
2022-12-31
More recent knowledge cutoff means awareness of newer technologies and frameworks
Provider Availability & Performance
Available providers and their performance metrics
+
+
+
+
Claude 3.5 Sonnet
3 providers
Anthropic
Throughput: 100 tok/s
Latency: 0.5ms
Bedrock
Throughput: 101 tok/s
Latency: 0.5ms
Throughput: 42 tok/s
Latency: 0.4ms
+
+
+
+
+
+
+
Claude 3.5 Sonnet
Avg Score:84.7%(+20.3%)
Providers:3
+
+
+
+
GPT-4
Avg Score:64.4%
Providers:2