Back to all models
C

Claude 3.5 Haiku

AnthropicReleased 2024-10-22
Official Page

Anthropic's fastest and most affordable model in the 3.5 family. Near-Sonnet intelligence at a fraction of the cost and latency.

Overall Score
76%
Cost Efficiency
100
Context Window
200K

Strengths

  • ✓Very fast inference
  • ✓Extremely affordable
  • ✓Good intelligence-to-cost ratio
  • ✓Strong coding for price

Weaknesses

  • ✗Lower performance than Sonnet
  • ✗Limited complex reasoning
Architecture
Transformer
Parameters
Unknown
Input
$1/M
Output
$5/M

Benchmark Performance

BenchmarkDescriptionScoreCategoryBar
MMLUMassive Multitask Language Understanding85.6%knowledge
HumanEvalCode generation accuracy88.5%coding
MATHMathematical reasoning84.1%math
GSM8KGrade school math86.7%math
GPQAGraduate-level science Q&A50.1%reasoning
HellaSwagCommon sense reasoning86.9%reasoning
SWE-benchSoftware engineering problems34.8%coding
ARC-CAI2 Reasoning Challenge94%reasoning
AI
ModelBench

The open benchmark platform for comparing the latest AI models and their capabilities.

Platform

  • Compare Models
  • All Models
  • Methodology

AI Labs

  • OpenAI
  • Anthropic
  • Google DeepMind
  • Meta AI

Resources

  • Documentation
  • Benchmark Guide
  • API Reference
Benchmarks are sourced from official model cards and independent evaluations. Data is for informational purposes only.
© 2026 ModelBench. Built for the AI community.