Back to all models
C

Claude 3.5 Sonnet

AnthropicReleased 2024-06-20
Official Page

Anthropic's most intelligent model in the 3.5 family, featuring Artifacts for creating and editing applications in real-time.

Overall Score
81%
Cost Efficiency
100
Context Window
200K

Strengths

  • ✓Excellent coding and computer use
  • ✓Artifacts feature
  • ✓Strong safety alignment
  • ✓Good value

Weaknesses

  • ✗Slightly lower math scores
  • ✗No native image generation
Architecture
Transformer
Parameters
~81B activated (MoE)
Input
$3/M
Output
$15/M

Benchmark Performance

BenchmarkDescriptionScoreCategoryBar
MMLUMassive Multitask Language Understanding88.3%knowledge
HumanEvalCode generation accuracy92%coding
MATHMathematical reasoning88.3%math
GSM8KGrade school math90%math
GPQAGraduate-level science Q&A59.4%reasoning
HellaSwagCommon sense reasoning88.7%reasoning
SWE-benchSoftware engineering problems43.3%coding
ARC-CAI2 Reasoning Challenge96%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.