Qwen2.5 32B: Complete Benchmark Performance Guide

alibaba 2.5-32b 2024-09-19 Qwen License

In-depth analysis of Qwen2.5 32B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendoralibaba
Version2.5-32b
Release Date2024-09-19
Context Window131072 tokens
Input Modalitiestext
Output Modalitiestext
LicenseQwen License
Documentationhttps://qwenlm.github.io/

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU78.5%2024-09-195-shotview
HUMANEVAL68pass@12024-09-19—view
GSM8K76.3%2024-09-190-shot CoTview
MATH39.5%2024-09-190-shot CoTview
BBH76.8%2024-09-193-shot CoTview
GPQA39.4%2024-09-190-shotview
IFEVAL73.5%2024-09-19prompt_strictview
ARC93.9%2024-09-19challengeview
MUSR54.9%2024-09-190-shotview
WINOGRANDE81.9%2024-09-190-shotview

Pricing

TierPriceCurrency
Input$0.35 / MtokUSD
Output$0.45 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://help.aliyun.com/zh/model-studio/getting-started/models · as of 2024-09-19

Compliance

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

Qwen2.5 32B

Model Genel Bakışı

阿里巴巴 Qwen2.5 32B 开源中端模型, 131K 上下文, 性能接近 72B, 适合中等规模部署。

Temel Özellikler

SatıcıSürümYayın TarihiBağlam PenceresiGiriş ModlarıÇıkış ModlarıLisans
Alibaba2.5-32b2024-09-19131KtexttextQwen License

Benchmark Performansı

BenchmarkPuanBirimNotlar
MMLU (Massive Multitask Language Understanding)78.5%5-shot
HumanEval68.0pass@1—
GSM8K (Grade School Math 8K)76.3%0-shot CoT
MATH39.5%0-shot CoT
BBH (BIG-Bench Hard)76.8%3-shot CoT
GPQA39.4%0-shot
IFEval73.5%prompt_strict
ARC93.9%challenge
MUSR54.9%0-shot
WinoGrande81.9%0-shot

Fiyatlandırma

GirişÇıkışÖnbellek OkumaÖnbellek Yazma
————

milyon token başına

Güçlü Yönler

  • 可靠的通用模型。

Zayıf Yönler

  • 闭源专有模型，不支持自托管。

Kullanım Senaryoları

  • 代码生成与调试

Referanslar