TECHAGENT - MY AI LIFE
← LLM Models
74Score

Claude Sonnet 4.6

#10

Anthropic

Balanced intelligence and speed. Strong coding, analysis, multilingual tasks.

Official page →
📖Context200K tokens
🚀Speed85 tok/s
💵Input price$3.00/1M
💸Output price$15.00/1M

Benchmarks

Gray bar = dataset average
MMLU57 academic subjects
88.3%avg 81.8
GPQA DiamondPhD-level science questions
65.0%avg 50.4
HumanEvalPython code generation
92.0%avg 79.9
SWE-Bench VerifiedReal GitHub engineering tasks
57.0%avg 32.4
Composite ScoreScore = MMLU×20% + GPQA×30% + HumanEval×25% + SWE-Bench×25%74.4

More from Anthropic

Claude Opus 4.7
Score 82$5.000/1M→
Claude Haiku 4.5
Score 60$1.000/1M→
Anthropic Claude Haiku Latest
$1.000/1M→
Claude 3 Haiku
$0.250/1M→
Claude Opus 4
$15.000/1M→
Claude Opus 4.1
$15.000/1M→

API Providers

Anthropic
Input
$3.00/1M
Output
$15.00/1M
→
AWS Bedrock
Input
$3.00/1M
Output
$15.00/1M
→
Google Vertex
Input
$3.00/1M
Output
$15.00/1M
→
OpenRouter
Input
$3.00/1M
Output
$15.00/1M
→

Details

Provider
Anthropic
Parameters
-
Context
200K tokens
Speed
85 tok/s
Open Source
No
License
Proprietary
Released
Feb 2026

Reviews

No reviews yet

Log in to rate

← View all 376 models