Claude Sonnet 4.6
Anthropic · Released Feb 17, 2026
$3
Input price / MTok
#22 of 27$15
Output price / MTok
#21 of 271.0M
Context window
#7 of 2847
Tokens / sec
#21 of 2179.6
SWE-bench Verified
#4 of 1258.1
SWE-bench Pro
#6 of 989.9
GPQA Diamond
#7 of 1995.6
AIME 2025
#1 of 1074.5
MMMU
#5 of 872.5
OSWorld
#7 of 890.6
MRCR
#2 of 5Summary
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
| Benchmark | Score | Max | % | Rank | Source |
|---|---|---|---|---|---|
| SWE-bench Verified | 79.6 | 100 | 79.6% | #4/12 | Anthropic (self-reported in official sys... |
| SWE-bench Pro | 58.1 | 100 | 58.1% | #6/9 | Anthropic (self-reported in official sys... |
| GPQA Diamond | 89.9 | 100 | 89.9% | #7/19 | Anthropic (self-reported in official sys... |
| AIME 2025 | 95.6 | 100 | 95.6% | #1/10 | Anthropic (self-reported in official sys... |
| MMMU | 74.5 | 100 | 74.5% | #5/8 | Anthropic (self-reported in official sys... |
| OSWorld | 72.5 | 100 | 72.5% | #7/8 | Anthropic (self-reported in official sys... |
| MRCR | 90.6 | 100 | 90.6% | #2/5 | Anthropic (self-reported in official sys... |
Similar Models
Compare all 6 modelsModels with the most shared benchmark coverage and closest scores to Claude Sonnet 4.6.
Compare Claude Sonnet 4.6 side by side
Pre-filled with 5 similar models
Speed source: https://artificialanalysis.ai/models/claude-sonnet-4-6