Claude 3.5 Haiku
Zero-eval
by Anthropic
About
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.
Pricing Range
Input (per 1M)$0.80 -$1.00
Output (per 1M)$4.00 -$5.00
Providers3
Timeline
AnnouncedOct 22, 2024
ReleasedOct 22, 2024
Specifications
License & Family
License
Proprietary
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
9 benchmarks
Average Score
60.8%
Best Score
88.1%
High Performers (80%+)
3Performance Metrics
Max Context Window
400.0KAvg Throughput
82.0 tok/sAvg Latency
0msTop Categories
code
88.1%
math
77.5%
general
57.6%
agents
36.9%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
HumanEval
Rank #22 of 62
#19o1
88.1%
#20Qwen2.5 32B Instruct
88.4%
#21Qwen2.5-Coder 7B Instruct
88.4%
#22Claude 3.5 Haiku
88.1%
#23GPT-4.5
88.0%
#24Gemma 3 27B
87.8%
#25GPT-4o mini
87.2%
MGSM
Rank #15 of 31
#12Llama 3.2 90B Instruct
86.9%
#13GPT-4o mini
87.0%
#14Gemini 1.5 Pro
87.5%
#15Claude 3.5 Haiku
85.6%
#16Qwen3 235B A22B
83.5%
#17Claude 3 Sonnet
83.5%
#18Gemini 1.5 Flash
82.6%
DROP
Rank #9 of 28
#6GPT-4o
83.4%
#7Llama 3.1 405B Instruct
84.8%
#8Nova Pro
85.4%
#9Claude 3.5 Haiku
83.1%
#10Claude 3 Opus
83.1%
#11GPT-4
80.9%
#12Nova Lite
80.2%
MATH
Rank #35 of 63
#32Mistral Small 3.2 24B Instruct
69.4%
#33Kimi K2 Base
70.2%
#34GPT-4o mini
70.2%
#35Claude 3.5 Haiku
69.4%
#36Nova Micro
69.3%
#37Mistral Small 3.1 24B Instruct
69.3%
#38Llama 3.2 90B Instruct
68.0%
MMLU-Pro
Rank #35 of 60
#32Mistral Small 3 24B Instruct
66.3%
#33Llama 3.1 70B Instruct
66.4%
#34Mistral Small 3.1 24B Instruct
66.8%
#35Claude 3.5 Haiku
65.0%
#36Qwen2 72B Instruct
64.4%
#37Qwen2.5 14B Instruct
63.7%
#38Gemma 3 12B
60.6%
All Benchmark Results for Claude 3.5 Haiku
Complete list of benchmark scores with detailed information
HumanEval HumanEval benchmark | code | text | 0.88 | 88.1% | Self-reported |
MGSM MGSM benchmark | math | text | 0.86 | 85.6% | Self-reported |
DROP DROP benchmark | general | text | 0.83 | 83.1% | Self-reported |
MATH MATH benchmark | math | text | 0.69 | 69.4% | Self-reported |
MMLU-Pro MMLU-Pro benchmark | general | text | 0.65 | 65.0% | Self-reported |
TAU-bench Retail TAU-bench Retail benchmark | agents | text | 0.51 | 51.0% | Self-reported |
GPQA GPQA benchmark | general | text | 0.42 | 41.6% | Self-reported |
SWE-Bench Verified SWE-Bench Verified benchmark | general | text | 0.41 | 40.6% | Self-reported |
TAU-bench Airline TAU-bench Airline benchmark | agents | text | 0.23 | 22.8% | Self-reported |
Resources