Mistral 7B v0.3: Complete Benchmark Performance Guide

mistral 7b-v0.3 2024-05-22 Apache 2.0

In-depth analysis of Mistral 7B v0.3 performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendormistral
Version7b-v0.3
Release Date2024-05-22
Context Window32768 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://docs.mistral.ai/

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU72.6%2024-05-225-shotview
HUMANEVAL68.8pass@12024-05-22—view
GSM8K69.4%2024-05-220-shot CoTview
MATH26.7%2024-05-220-shot CoTview
BBH60.5%2024-05-223-shot CoTview
GPQA31.2%2024-05-220-shotview
IFEVAL60.9%2024-05-22prompt_strictview
ARC88.9%2024-05-22challengeview
MUSR48.1%2024-05-220-shotview
WINOGRANDE72.7%2024-05-220-shotview

Pricing

TierPriceCurrency
Input$0.18 / MtokUSD
Output$0.18 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://mistral.ai/technology/ · as of 2024-05-22

Compliance

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

Mistral 7B v0.3

Visão geral do modelo

Mistral 7B v0.3 开源模型, 32K 上下文, 改进 v0.2, 扩展词汇表至 32768, 适合本地部署。

Especificações principais

FornecedorVersãoData de lançamentoJanela de contextoModalidades de entradaModalidades de saídaLicença
Mistral7b-v0.32024-05-2232KtexttextApache 2.0

Desempenho em benchmarks

BenchmarkPontuaçãoUnidadeNotas
MMLU (Massive Multitask Language Understanding)72.6%5-shot
HumanEval68.8pass@1—
GSM8K (Grade School Math 8K)69.4%0-shot CoT
MATH26.7%0-shot CoT
BBH (BIG-Bench Hard)60.5%3-shot CoT
GPQA31.2%0-shot
IFEval60.9%prompt_strict
ARC88.9%challenge
MUSR48.1%0-shot
WinoGrande72.7%0-shot

Preços

EntradaSaídaLeitura de cacheEscrita de cache
————

por milhão de tokens

Pontos fortes

  • 可靠的通用模型。

Pontos fracos

  • 闭源专有模型，不支持自托管。

Casos de uso

  • 通用对话与问答

Referências