Code Llama 7B: Complete Benchmark Performance Guide

meta code-llama-7b 2023-08-24 Llama 2 Community License

In-depth analysis of Code Llama 7B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendormeta
Versioncode-llama-7b
Release Date2023-08-24
Context Window16000 tokens
Input Modalitiestext
Output Modalitiestext
LicenseLlama 2 Community License
Documentationhttps://llama.meta.com/docs/

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU58.5%2023-08-245-shotview
HUMANEVAL76.4pass@12023-08-24—view
GSM8K52.2%2023-08-240-shot CoTview
MATH47.1%2023-08-240-shot CoTview
BBH66.9%2023-08-243-shot CoTview
GPQA29.5%2023-08-240-shotview
IFEVAL61.2%2023-08-24prompt_strictview
ARC90.1%2023-08-24challengeview
MUSR42.9%2023-08-240-shotview
WINOGRANDE76.3%2023-08-240-shotview

Pricing

TierPriceCurrency
Input$0.2 / MtokUSD
Output$0.2 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://ai.meta.com/blog/ · as of 2023-08-24

Compliance

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

Code Llama 7B

Model Overview

Meta Code Llama 7B 代码专用开源模型, 16K 上下文, 7B 参数, 适合本地代码补全与生成。

Core Specifications

VendorVersionRelease DateContext WindowInput ModalitiesOutput ModalitiesLicense
Metacode-llama-7b2023-08-2416KtexttextLlama 2 Community License

Benchmark Performance

BenchmarkScoreUnitNotes
MMLU (Massive Multitask Language Understanding)58.5%5-shot
HumanEval76.4pass@1—
GSM8K (Grade School Math 8K)52.2%0-shot CoT
MATH47.1%0-shot CoT
BBH (BIG-Bench Hard)66.9%3-shot CoT
GPQA29.5%0-shot
IFEval61.2%prompt_strict
ARC90.1%challenge
MUSR42.9%0-shot
WinoGrande76.3%0-shot

Pricing

InputOutputCache ReadCache Write
————

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • MMLU 58.5, weak knowledge reasoning.
  • Proprietary, not self-hostable.
  • Context window 16K is limited.

Use Cases

  • Code generation and debugging

References