Anthropic logo

Claude Sonnet 4.6

Anthropic · Released Feb 17, 2026

ProprietarycodingagentsvisionCompare this model

$3

Input price / MTok

#22 of 27

$15

Output price / MTok

#21 of 27

1.0M

Context window

#7 of 28

47

Tokens / sec

#21 of 21

79.6

SWE-bench Verified

#4 of 12

58.1

SWE-bench Pro

#6 of 9

89.9

GPQA Diamond

#7 of 19

95.6

AIME 2025

#1 of 10

74.5

MMMU

#5 of 8

72.5

OSWorld

#7 of 8

90.6

MRCR

#2 of 5

Summary

Claude Sonnet 4.6 is a proprietary language model from Anthropic, released on Feb 17, 2026.

At $3 input and $15 output per million tokens, it ranks #22 of 27 for input price, placing it mid-range on input cost.

Its context window of 1.0M tokens ranks #7 of 28 for context depth in this dataset.

It targets coding, agents, vision workloads.

Throughput is measured at 47 tokens per second (ranked #21 of 21 for throughput).

Benchmarks

BenchmarkScoreMax%RankSource
SWE-bench Verified79.610079.6%#4/12Anthropic (self-reported in official sys...
SWE-bench Pro58.110058.1%#6/9Anthropic (self-reported in official sys...
GPQA Diamond89.910089.9%#7/19Anthropic (self-reported in official sys...
AIME 202595.610095.6%#1/10Anthropic (self-reported in official sys...
MMMU74.510074.5%#5/8Anthropic (self-reported in official sys...
OSWorld72.510072.5%#7/8Anthropic (self-reported in official sys...
MRCR90.610090.6%#2/5Anthropic (self-reported in official sys...

Similar Models

Compare all 6 models

Models with the most shared benchmark coverage and closest scores to Claude Sonnet 4.6.

Claude Sonnet 4.6
GoogleGemini 2.5 Pro
OpenAIGPT-5
OpenAIo3
OpenAIGPT-5.5
OpenAIo4-mini
SWE-bench Verified#4 of 12
Real-world GitHub issue resolution
GPQA Diamond#7 of 19
Graduate-level science reasoning
AIME 2025#1 of 10
Advanced math competition problems
MMMU#5 of 8
Multimodal understanding across 30 subjects
MRCR#2 of 5
Long-context retrieval and recall
SWE-bench Pro#6 of 9
Professional software engineering tasks
OSWorld#7 of 8
Computer-use and GUI automation

Compare Claude Sonnet 4.6 side by side

Pre-filled with 5 similar models

Open comparison

Speed source: https://artificialanalysis.ai/models/claude-sonnet-4-6