Claude Sonnet 4.6
제공 Anthropic · 출시일 2026-02-17
47.6
평균 점수
$3.00/1M
입력 가격
$15.00/1M
출력 가격
1.0M tokens (~500 books)
컨텍스트 윈도우
multimodal
유형
Tested on 18 benchmarks with 47.6% average. Top scores: Chatbot Arena Elo — Coding (1521.0%), Chatbot Arena Elo — Overall (1462.2%), ARC-AGI (86.5%).
벤치마크 점수
| 벤치마크 | 카테고리 | 점수 | Bar |
|---|---|---|---|
| Chatbot Arena Elo — Coding | arena | 1521.0 | |
| Chatbot Arena Elo — Overall | arena | 1462.2 | |
| ARC-AGI | reasoning | 86.5 | |
| OTIS Mock AIME 2024-2025 | math | 85.8 | |
| GPQA diamond | knowledge | 83.2 | |
| SWE-Bench verified | coding | 75.2 | |
| WeirdML | coding | 66.1 | |
| Artificial Analysis — Agentic Index | speed | 63.0 | |
| ARC-AGI-2 | reasoning | 60.4 | |
| Artificial Analysis — Quality Index | speed | 51.7 | |
| Artificial Analysis — Coding Index | speed | 50.9 | |
| FrontierMath-2025-02-28-Private | math | 32.4 | |
| SWE Atlas — Test Writing | agentic | 31.8 | |
| SWE Atlas — Codebase QnA | agentic | 31.2 | |
| SimpleQA Verified | knowledge | 29.0 | |
| PostTrainBench | knowledge | 16.4 | |
| Chess Puzzles | knowledge | 13.0 | |
| FrontierMath-Tier-4-2025-07-01-Private | math | 8.3 |
유사 모델
Anthropic
47.7
U
Stable Beluga 2Unknown
47.8
Google DeepMind
47.4
Alibaba
47.3