GLM-4 Plus: Complete Benchmark Performance Guide

other glm-4-plus 2024-08-12 Proprietary

In-depth analysis of GLM-4 Plus performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionglm-4-plus
Release Date2024-08-12
Context Window131072 tokens
Input Modalitiestext, image
Output Modalitiestext
LicenseProprietary
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU84.3%2024-08-125-shotview
HUMANEVAL72.7pass@12024-08-12—view
GSM8K81.8%2024-08-120-shot CoTview
MATH53.3%2024-08-120-shot CoTview
BBH83.6%2024-08-123-shot CoTview
GPQA35.4%2024-08-120-shotview
IFEVAL79.2%2024-08-12prompt_strictview
ARC94.5%2024-08-12challengeview
MUSR51.3%2024-08-120-shotview
WINOGRANDE85.8%2024-08-120-shotview

Pricing

TierPriceCurrency
Input$0.5 / MtokUSD
Output$0.5 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-08-12

Compliance

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

GLM-4 Plus

Model Overview

清华智谱 GLM-4 Plus 旗舰模型, 131K 上下文, 支持文本与图像输入, 中文能力突出。

Core Specifications

VendorVersionRelease DateContext WindowInput ModalitiesOutput ModalitiesLicense
Otherglm-4-plus2024-08-12131Ktext, imagetextProprietary

Benchmark Performance

BenchmarkScoreUnitNotes
MMLU (Massive Multitask Language Understanding)84.3%5-shot
HumanEval72.7pass@1—
GSM8K (Grade School Math 8K)81.8%0-shot CoT
MATH53.3%0-shot CoT
BBH (BIG-Bench Hard)83.6%3-shot CoT
GPQA35.4%0-shot
IFEval79.2%prompt_strict
ARC94.5%challenge
MUSR51.3%0-shot
WinoGrande85.8%0-shot

Pricing

InputOutputCache ReadCache Write
————

per million tokens

Strengths

  • MMLU score 84.3, strong knowledge reasoning.
  • Input Modalities: text, image, audio.

Weaknesses

  • Proprietary, not self-hostable.

Use Cases

  • Code generation and debugging
  • Vision and image understanding
  • Agent workflows and tool use

References