Key Specifications

Vendorxai
Versionbeta
Release Date2023-11-04
Context Window8192 tokens
Input Modalitiestext
Output Modalitiestext
LicenseProprietary
Documentationhttps://docs.x.ai/

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU51%2023-11-045-shotview
HUMANEVAL31pass@12023-11-04view
GSM8K48.7%2023-11-040-shot CoTview
MATH19.1%2023-11-040-shot CoTview
BBH50.2%2023-11-043-shot CoTview
GPQA20.6%2023-11-040-shotview
IFEVAL56.2%2023-11-04prompt_strictview
ARC81.7%2023-11-04challengeview
MUSR43.7%2023-11-040-shotview
WINOGRANDE69.2%2023-11-040-shotview

Pricing

TierPriceCurrency
Input$1 / MtokUSD
Output$5 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://x.ai/api · as of 2023-11-04

Compliance

  • Data Residency: US
  • SOC2: ✗
  • HIPAA: ✗
  • GDPR: ✗
  • ISO 27001: ✗

Grok Beta

모델 개요

xAI Grok Beta 早期预览版, 8K 上下文, 集成 X 平台实时数据, 幽默风格对话能力突出。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Xaibeta2023-11-048KtexttextProprietary

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)51.0%5-shot
HumanEval31.0pass@1
GSM8K (Grade School Math 8K)48.7%0-shot CoT
MATH19.1%0-shot CoT
BBH (BIG-Bench Hard)50.2%3-shot CoT
GPQA20.6%0-shot
IFEval56.2%prompt_strict
ARC81.7%challenge
MUSR43.7%0-shot
WinoGrande69.2%0-shot

가격

입력출력캐시 읽기캐시 쓰기

백만 토큰당

강점

  • 可靠的通用模型。

약점

  • MMLU 仅 51.0,知识推理偏弱。
  • HumanEval 31.0,代码能力较弱。
  • 闭源专有模型,不支持自托管。
  • 上下文窗口 8K 偏小。

사용 사례

  • 通用对话与问答

참고문헌