Best Coding Model
AnthropicProvisional

Claude Sonnet 5

Claude 5 / Sonnet · claude-sonnet-5

Broadly available Claude model for everyday agentic coding and product work.

Objective score

34.6

Confidence

79%

Price evidence

$2 input / $10 output per 1M tokens intro

Other primary tiers in this family

FableSonnet

Evidence state

Signal coverage

Benchmarks
2
Rank points
7
Usage
2
Agent
0
Sources
4

Objective evidence

Benchmarks and public signals

Swebench
Livecodebench
Aider
Artificial Analysis
71.5
Openrouter Usage
3.2
Kilo Usage

Persistent history

Recent ranking points

Aug 1#32 · 37
Aug 1#32 · 37
Jul 31#32 · 37
Jul 31#32 · 37
Jul 31#32 · 37
Jul 31#32 · 37

Usage signals

OpenRouter3.2%
Overall2.1%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.