StableCode 3B: Complete Benchmark Performance Guide

other stablecode-3b 2024-01-19 Stability AI Community License

In-depth analysis of StableCode 3B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionstablecode-3b
Release Date2024-01-19
Context Window100000 tokens
Input Modalitiestext
Output Modalitiestext
LicenseStability AI Community License
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU77.4%2024-01-195-shotview
HUMANEVAL77pass@12024-01-19—view
GSM8K68.5%2024-01-190-shot CoTview
MATH31%2024-01-190-shot CoTview
BBH58.4%2024-01-193-shot CoTview
GPQA24.5%2024-01-190-shotview
IFEVAL51.8%2024-01-19prompt_strictview
ARC86.4%2024-01-19challengeview
MUSR51.8%2024-01-190-shotview
WINOGRANDE70.9%2024-01-190-shotview

Pricing

TierPriceCurrency
Input$0.12 / MtokUSD
Output$0.12 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-01-19

Compliance

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

StableCode 3B

Aperçu du modèle

Stability AI StableCode 3B 代码专用模型, 100K 上下文, 3B 参数, 支持多种编程语言代码补全。

Spécifications principales

FournisseurVersionDate de sortieFenêtre de contexteModalités d’entréeModalités de sortieLicence
Otherstablecode-3b2024-01-19100KtexttextStability AI Community License

Performance aux benchmarks

BenchmarkScoreUnitéNotes
MMLU (Massive Multitask Language Understanding)77.4%5-shot
HumanEval77.0pass@1—
GSM8K (Grade School Math 8K)68.5%0-shot CoT
MATH31.0%0-shot CoT
BBH (BIG-Bench Hard)58.4%3-shot CoT
GPQA24.5%0-shot
IFEval51.8%prompt_strict
ARC86.4%challenge
MUSR51.8%0-shot
WinoGrande70.9%0-shot

Tarification

EntréeSortieLecture cacheÉcriture cache
————

par million de jetons

Forces

  • 上下文窗口 100K，支持长文本。

Faiblesses

  • 闭源专有模型，不支持自托管。

Cas d’usage

  • 代码生成与调试
  • 长文档摘要

Références