+
+
+
+
+
+
+
+
VS
VS
VS
VS
VS
VS
Claude 3.5 Haiku vs Claude Sonnet 4.5
Comprehensive side-by-side LLM comparison
Claude Sonnet 4.5 leads with 9.6% higher average benchmark score. Claude 3.5 Haiku offers 136.0K more tokens in context window than Claude Sonnet 4.5. Claude 3.5 Haiku is $13.20 cheaper per million tokens. Claude Sonnet 4.5 supports multimodal inputs. Overall, Claude Sonnet 4.5 is the stronger choice for coding tasks.
+
+
+
+
Anthropic
Claude 3.5 Haiku is a language model developed by Anthropic. It achieves strong performance with an average score of 60.8% across 9 benchmarks. It excels particularly in HumanEval (88.1%), MGSM (85.6%), DROP (83.1%). It supports a 400K token context window for handling large documents. The model is available through 3 API providers. Released in 2024, it represents Anthropic's latest advancement in AI technology.
+
+
+
+
Anthropic
Claude Sonnet 4.5 is a multimodal language model developed by Anthropic. It achieves strong performance with an average score of 75.8% across 9 benchmarks. It excels particularly in MMMLU (89.1%), AIME 2025 (87.0%), TAU-bench Retail (86.2%). 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.
11 months newer
Claude 3.5 Haiku
Anthropic
2024-10-22
Claude Sonnet 4.5
Anthropic
2025-09-29
Pricing Comparison
Cost per million tokens (USD)
+
+
+
+
Claude 3.5 Haiku
Input:$0.80
Output:$4.00($13.20 cheaper)
+
+
+
+
Claude Sonnet 4.5
Input:$3.00
Output:$15.00
Performance Metrics
Context window and performance specifications
Average performance across 14 common benchmarks
+
+
+
+
Claude 3.5 Haiku
Average Score:39.1%
+
+
+
+
Claude Sonnet 4.5
Average Score:48.7%(+9.6%)
+
+
+
+
Knowledge Cutoff
Training data recency comparison
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
+
+
+
+
Claude 3.5 Haiku
3 providers
Anthropic
Throughput: 100 tok/s
Latency: 0.3ms
Bedrock
Throughput: 104 tok/s
Latency: 0.5ms
Throughput: 42 tok/s
Latency: 0.4ms
+
+
+
+
+
+
+
Claude 3.5 Haiku
Avg Score:39.1%
Providers:3
+
+
+
+
Claude Sonnet 4.5
Avg Score:48.7%(+9.6%)
Providers:2