WizardLM Team WizardLM 2 8x22B: Complete Benchmark Performance Guide

other wizardlmteam-wizardlm-2-8x22b 2024-04-15 Apache 2.0

In-depth analysis of WizardLM Team WizardLM 2 8x22B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionwizardlmteam-wizardlm-2-8x22b
Release Date2024-04-15
Context Window65536 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 79.2 % 2024-04-15 5-shot view
HUMANEVAL 70.2 pass@1 2024-04-15 — view
GSM8K 77.9 % 2024-04-15 0-shot CoT view
MATH 37.4 % 2024-04-15 0-shot CoT view
BBH 80 % 2024-04-15 3-shot CoT view
GPQA 41.4 % 2024-04-15 0-shot view
IFEVAL 70.7 % 2024-04-15 prompt_strict view
ARC 92.3 % 2024-04-15 challenge view
MUSR 56.8 % 2024-04-15 0-shot view
WINOGRANDE 83.5 % 2024-04-15 0-shot view

Pricing

Tier Price Currency
Input$1.2 / MtokUSD
Output$1.2 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-04-15

Compliance

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

WizardLM Team WizardLM 2 8x22B

Model Overview

WizardLM Team WizardLM 2 8x22B 官方发布版, 64K 上下文, 基于 Mixtral 8x22B 微调, Arena 上接近 GPT-4。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other wizardlmteam-wizardlm-2-8x22b 2024-04-15 65K text text Apache 2.0

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 79.2 % 5-shot
HumanEval 70.2 pass@1 —
GSM8K (Grade School Math 8K) 77.9 % 0-shot CoT
MATH 37.4 % 0-shot CoT
BBH (BIG-Bench Hard) 80.0 % 3-shot CoT
GPQA 41.4 % 0-shot
IFEval 70.7 % prompt_strict
ARC 92.3 % challenge
MUSR 56.8 % 0-shot
WinoGrande 83.5 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Mixture-of-Experts architecture.

Weaknesses

  • Proprietary, not self-hostable.

Use Cases

  • Code generation and debugging

References