Key Specifications

SpecificationLlama 3.1 8BMistral 7B v0.3
Vendormetamistral
Version3.1-8b7b-v0.3
Release Date2024-07-232024-05-22
Context Window128000 tokens32768 tokens
Input Modalitiestexttext
Output Modalitiestexttext
LicenseLlama 3 Community LicenseApache 2.0
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkLlama 3.1 8BMistral 7B v0.3Winner
ARC87.488.9Mistral 7B v0.3
BBH67.160.5Llama 3.1 8B
GPQA34.831.2Llama 3.1 8B
GSM8K58.869.4Mistral 7B v0.3
HUMANEVAL63.468.8Mistral 7B v0.3
IFEVAL62.160.9Llama 3.1 8B
MATH31.126.7Llama 3.1 8B
MMLU7372.6Llama 3.1 8B
MUSR41.748.1Mistral 7B v0.3
WINOGRANDE77.672.7Llama 3.1 8B

Pricing Comparison

Tier (per Mtok)Llama 3.1 8BMistral 7B v0.3
Input$0.18$0.18
Output$0.18$0.18
Cache Read$0$0
Cache Write$0$0

Llama 3.1 8B против Mistral 7B v0.3

Обзор модели

Llama 3.1 8B and Mistral 7B v0.3 are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Ключевые характеристики

ПоставщикДата выпускаОкно контекстаЛицензия
Meta / Mistral2024-07-23 / 2024-05-22128K / 32KLlama 3 Community License / Apache 2.0

Производительность

БенчмаркLlama 3.1 8BMistral 7B v0.3Победитель
ARC87.488.9B
BBH (BIG-Bench Hard)67.160.5A
GPQA34.831.2A
GSM8K (Grade School Math 8K)58.869.4B
HumanEval63.468.8B
IFEval62.160.9A
MATH31.126.7A
MMLU (Massive Multitask Language Understanding)73.072.6Tie
MUSR41.748.1B
WinoGrande77.672.7A

Сравнение цен

ВходВыходЧтение кэшаЗапись кэша
— / —— / —— / —— / —

за миллион токенов — A / B

Сильные стороны & Слабые стороны

Llama 3.1 8B

  • ✅ 可靠的通用模型。
  • ⚠️ 闭源专有模型,不支持自托管。

Mistral 7B v0.3

  • ✅ 可靠的通用模型。
  • ⚠️ 闭源专有模型,不支持自托管。

Мнение редактора

Llama 3.1 8B and Mistral 7B v0.3 each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.

ЧЗВ

Which model is better for coding tasks?

Refer to the HumanEval benchmark table; the model with a higher score is better suited for coding tasks.

Which model is cheaper?

Refer to the pricing comparison table above; the model with lower input/output prices is more cost-effective.

Which has a longer context window?

Refer to the key specifications table; the model with a larger context window is better for long documents.

Ссылки

Editor's Take

See Editor's Take section.