Claude Sonnet 4
제공 Anthropic · 출시일 2025-05-22
44.6
평균 점수
$3.00/1M
입력 가격
$15.00/1M
출력 가격
1.0M tokens (~500 books)
컨텍스트 윈도우
multimodal
유형
Tested on 27 benchmarks with 44.6% average. Top scores: MASK (95.3%), OpenCompass — IFEval (88.3%), MATH level 5 (84.4%).
벤치마크 점수
| 벤치마크 | 카테고리 | 점수 | Bar |
|---|---|---|---|
| MASK | safety | 95.3 | |
| OpenCompass — IFEval | language | 88.3 | |
| MATH level 5 | math | 84.4 | |
| OpenCompass — MMLU-Pro | knowledge | 83.0 | |
| OpenCompass — GPQA-Diamond | knowledge | 74.6 | |
| GPQA diamond | knowledge | 72.3 | |
| OTIS Mock AIME 2024-2025 | math | 71.1 | |
| OpenCompass — AIME2025 | math | 68.7 | |
| SWE-Bench Verified (Bash Only) | coding | 64.9 | |
| Aider polyglot | coding | 61.3 | |
| DeepResearch Bench | knowledge | 47.8 | |
| OpenCompass — LiveCodeBenchV6 | coding | 47.5 | |
| Fiction.LiveBench | knowledge | 46.9 | |
| WeirdML | coding | 46.1 | |
| OSWorld | agentic | 43.9 | |
| ARC-AGI | reasoning | 40.0 | |
| GeoBench | knowledge | 37.0 | |
| Cybench | coding | 35.0 | |
| SimpleBench | reasoning | 34.6 | |
| The Agent Company | agentic | 33.1 | |
| OpenCompass — HLE | knowledge | 8.7 | |
| ARC-AGI-2 | reasoning | 5.9 | |
| GSO-Bench | coding | 4.9 | |
| FrontierMath-2025-02-28-Private | math | 4.1 | |
| HLE | knowledge | 3.1 | |
| VPCT | knowledge | 1.0 | |
| FrontierMath-Tier-4-2025-07-01-Private | math | 0.1 |
유사 모델
OpenAI
44.5
Alibaba Qwen
44.4
TII
44.4
Meta
44.2