Key Specifications

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

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 63.3 % 2023-11-04 5-shot view
HUMANEVAL 44 pass@1 2023-11-04 view
GSM8K 35.2 % 2023-11-04 0-shot CoT view
MATH 24 % 2023-11-04 0-shot CoT view
BBH 56.8 % 2023-11-04 3-shot CoT view
GPQA 32.4 % 2023-11-04 0-shot view
IFEVAL 46.8 % 2023-11-04 prompt_strict view
ARC 88.2 % 2023-11-04 challenge view
MUSR 44.5 % 2023-11-04 0-shot view
WINOGRANDE 67.5 % 2023-11-04 0-shot view

Pricing

Tier Price Currency
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 Vision Beta

Model Overview

xAI Grok Vision Beta 早期多模态预览版, 8K 上下文, 支持图像理解, 集成 X 平台实时信息。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Xai vision-beta 2023-11-04 8K text, image text Proprietary

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 63.3 % 5-shot
HumanEval 44.0 pass@1
GSM8K (Grade School Math 8K) 35.2 % 0-shot CoT
MATH 24.0 % 0-shot CoT
BBH (BIG-Bench Hard) 56.8 % 3-shot CoT
GPQA 32.4 % 0-shot
IFEval 46.8 % prompt_strict
ARC 88.2 % challenge
MUSR 44.5 % 0-shot
WinoGrande 67.5 % 0-shot

Pricing

Input Output Cache Read Cache Write

per million tokens

Strengths

  • Input Modalities: text, image, audio.

Weaknesses

  • HumanEval 44.0, coding weak.
  • Proprietary, not self-hostable.
  • Context window 8K is limited.

Use Cases

  • Vision and image understanding

References