Llama 2 13B: Complete Benchmark Performance Guide

meta 2-13b 2023-07-18 Llama 2 Community License

In-depth analysis of Llama 2 13B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendormeta
Version2-13b
Release Date2023-07-18
Context Window4096 tokens
Input Modalitiestext
Output Modalitiestext
LicenseLlama 2 Community License
Documentationhttps://llama.meta.com/docs/

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU56.4%2023-07-185-shotview
HUMANEVAL40.7pass@12023-07-18—view
GSM8K34.6%2023-07-180-shot CoTview
MATH25.9%2023-07-180-shot CoTview
BBH62.1%2023-07-183-shot CoTview
GPQA22.3%2023-07-180-shotview
IFEVAL49.9%2023-07-18prompt_strictview
ARC89.5%2023-07-18challengeview
MUSR33.8%2023-07-180-shotview
WINOGRANDE76.4%2023-07-180-shotview

Pricing

TierPriceCurrency
Input$0.3 / MtokUSD
Output$0.3 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://ai.meta.com/blog/ · as of 2023-07-18

Compliance

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

Llama 2 13B

Model Overview

Meta Llama 2 13B 中型开源模型, 4K 上下文, 13B 参数, 平衡性能与资源消耗, 适合中等规模部署。

Core Specifications

VendorVersionRelease DateContext WindowInput ModalitiesOutput ModalitiesLicense
Meta2-13b2023-07-184KtexttextLlama 2 Community License

Benchmark Performance

BenchmarkScoreUnitNotes
MMLU (Massive Multitask Language Understanding)56.4%5-shot
HumanEval40.7pass@1—
GSM8K (Grade School Math 8K)34.6%0-shot CoT
MATH25.9%0-shot CoT
BBH (BIG-Bench Hard)62.1%3-shot CoT
GPQA22.3%0-shot
IFEval49.9%prompt_strict
ARC89.5%challenge
MUSR33.8%0-shot
WinoGrande76.4%0-shot

Pricing

InputOutputCache ReadCache Write
————

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • MMLU 56.4, weak knowledge reasoning.
  • HumanEval 40.7, coding weak.
  • Proprietary, not self-hostable.
  • Context window 4K is limited.

Use Cases

  • General chat and Q&A

References