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

모델 개요

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。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Metacode-llama-7b2023-08-2416KtexttextLlama 2 Community License

벤치마크 성능

벤치마크점수단위비고
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

가격

입력출력캐시 읽기캐시 쓰기
————

백만 토큰당

강점

  • 可靠的通用模型。

약점

  • MMLU 仅 58.5，知识推理偏弱。
  • 闭源专有模型，不支持自托管。
  • 上下文窗口 16K 偏小。

사용 사례

  • 代码生成与调试

참고문헌