01Overview02Models03Rankings04Compare05Quiz06Guide

Model

Claude Sonnet 4.6 NO.04

The production workhorse — best balance of speed and intelligence.

CompareBack to the index

Anthropic · Claude · Balanced · Closed weights

Specification

Fig.01 — Claude — Anthropic

USA

Context window
1Mtokens
Max output
64Ktokens
Input price
$3/ 1M
Output price
$15/ 1M
Cached input
$0.30/ 1M
Throughput
—
Class
Balanced
Modalities
Text, Image, Pdf
Weights
Closed
Knowledge cutoff
Nov 2025
Released
Feb 2026

Overview

Claude Sonnet 4.6 offers the best balance of speed and intelligence in the Claude lineup and is the default production workhorse for most agentic and coding workloads. It handles the large majority of real tasks reliably at a fraction of Opus pricing, escalating to Opus or Fable only for the hardest jobs. Its 1M context and strong tool use make it a dependable everyday driver.

Strengths

  • Excellent speed-to-intelligence balance
  • Reliable everyday agentic coding
  • 1M context at a moderate price
  • Strong tool use and instruction following

Trade-offs

  • Below Opus/Fable on the hardest long-horizon jobs
  • 64K max output cap
  • No audio/video input

Fit

Best for

  • Everyday production coding agents
  • High-volume developer workflows
  • Chat and assistant backends
  • RAG and document analysis

Not ideal for

  • The most demanding autonomous coding runs
  • Tasks needing very long single outputs

Capabilities

Ten axes, normalized 0–100 and scored the same way across the whole catalog — so a 78 here means what a 78 means anywhere else on the bench.

Fig.02 — Capability radar

0 — 100

Reasoning
89
Coding
89
Math
86
Writing
90
Knowledge
90
Speed
78
Agentic
88
Vision
84
Multilingual
89
Long Context
92

Benchmarks

Public results, with independent third-party runs marked. Bars normalize percentages against 100 and Elo ratings against a 1500 ceiling.

Independent index

Artificial Analysis Intelligence Index

Composite of ~9–10 independent evals · Artificial Analysis

47/ 100

BenchmarkResult
Artificial Analysis Intelligence IndexIndependentGeneral · Artificial Analysis
47%
SWE-bench VerifiedIndependentCoding · SWE-bench
79.6%
τ-benchIndependentAgentic · τ-bench
87.5%
LiveBenchIndependentGeneral · LiveBench
75.5%
GPQA DiamondIndependentReasoning · Independent aggregators
89.9%
DeepSWEIndependentCoding · Datacurve
32%
LMArena EloIndependentGeneral · LMArena
1467Elo

Alternatives

Models in roughly the same class — the ones worth weighing against this record.

Compare side by side
01GPT-5.6 TerraOpenAIThe GPT-5.6 balanced workhorse — GPT-5.5-class quality at half the price.02Gemini 3.5 FlashGoogle DeepMindFast, cheap multimodal workhorse with near-Pro quality.03Claude Opus 4.8AnthropicState-of-the-art autonomous coding reliability at half the price of Fable 5.

Index

PreviousClaude Opus 4.7NextClaude Sonnet 5
All models/EDUCATION