Command R (08-2024): Complete Benchmark Performance Guide

cohere r08-2024 2024-08-13 CC-BY-NC-4.0

In-depth analysis of Command R (08-2024) performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorcohere
Versionr08-2024
Release Date2024-08-13
Context Window128000 tokens
Input Modalitiestext
Output Modalitiestext
LicenseCC-BY-NC-4.0
Documentationhttps://docs.cohere.com/docs

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU77.8%2024-08-135-shotview
HUMANEVAL73.6pass@12024-08-13—view
GSM8K83.7%2024-08-130-shot CoTview
MATH47.1%2024-08-130-shot CoTview
BBH78.8%2024-08-133-shot CoTview
GPQA44.6%2024-08-130-shotview
IFEVAL70.3%2024-08-13prompt_strictview
ARC94.4%2024-08-13challengeview
MUSR49.1%2024-08-130-shotview
WINOGRANDE79.3%2024-08-130-shotview

Pricing

TierPriceCurrency
Input$0.15 / MtokUSD
Output$0.6 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://cohere.com/pricing · as of 2024-08-13

Compliance

  • Data Residency: US
  • SOC2: ✓
  • HIPAA: ✗
  • GDPR: ✓
  • ISO 27001: ✓

Command R (08-2024)

Visão geral do modelo

Cohere Command R 08-2024 版本, 128K 上下文, 改进 RAG 与工具调用能力, 支持结构化输出。

Especificações principais

FornecedorVersãoData de lançamentoJanela de contextoModalidades de entradaModalidades de saídaLicença
Coherer08-20242024-08-13128KtexttextCC-BY-NC-4.0

Desempenho em benchmarks

BenchmarkPontuaçãoUnidadeNotas
MMLU (Massive Multitask Language Understanding)77.8%5-shot
HumanEval73.6pass@1—
GSM8K (Grade School Math 8K)83.7%0-shot CoT
MATH47.1%0-shot CoT
BBH (BIG-Bench Hard)78.8%3-shot CoT
GPQA44.6%0-shot
IFEval70.3%prompt_strict
ARC94.4%challenge
MUSR49.1%0-shot
WinoGrande79.3%0-shot

Preços

EntradaSaídaLeitura de cacheEscrita de cache
————

por milhão de tokens

Pontos fortes

  • 企业级合规认证。

Pontos fracos

  • 闭源专有模型，不支持自托管。

Casos de uso

  • 代码生成与调试
  • 企业客户支持

Referências