Key Specifications

Vendorother
Versionsonar-large
Release Date2024-05-13
Context Window128000 tokens
Input Modalitiestext
Output Modalitiestext
LicenseProprietary
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU82.5%2024-05-135-shotview
HUMANEVAL80.4pass@12024-05-13view
GSM8K84.5%2024-05-130-shot CoTview
MATH51.6%2024-05-130-shot CoTview
BBH81.6%2024-05-133-shot CoTview
GPQA41.6%2024-05-130-shotview
IFEVAL74.9%2024-05-13prompt_strictview
ARC94.1%2024-05-13challengeview
MUSR65.6%2024-05-130-shotview
WINOGRANDE81.1%2024-05-130-shotview

Pricing

TierPriceCurrency
Input$1 / MtokUSD
Output$1 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-05-13

Compliance

  • Data Residency: self-host
  • SOC2: ✗
  • HIPAA: ✗
  • GDPR: ✗
  • ISO 27001: ✗

Sonar Large

모델 개요

Perplexity Sonar Large 在线 RAG 模型, 128K 上下文, 基于 Llama 3 70B 微调, 集成实时搜索。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Othersonar-large2024-05-13128KtexttextProprietary

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)82.5%5-shot
HumanEval80.4pass@1
GSM8K (Grade School Math 8K)84.5%0-shot CoT
MATH51.6%0-shot CoT
BBH (BIG-Bench Hard)81.6%3-shot CoT
GPQA41.6%0-shot
IFEval74.9%prompt_strict
ARC94.1%challenge
MUSR65.6%0-shot
WinoGrande81.1%0-shot

가격

입력출력캐시 읽기캐시 쓰기

백만 토큰당

강점

  • MMLU score 82.5, strong knowledge reasoning.
  • HumanEval 80.4, excellent code generation.
  • 企业级合规认证。

약점

  • 闭源专有模型,不支持自托管。

사용 사례

  • 代码生成与调试
  • 企业客户支持

참고문헌