Hermes 3 Llama 3.1 8B: Complete Benchmark Performance Guide

other hermes-3-llama-3-1-8b 2024-08-12 Llama 3.1 Community License

In-depth analysis of Hermes 3 Llama 3.1 8B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionhermes-3-llama-3-1-8b
Release Date2024-08-12
Context Window131072 tokens
Input Modalitiestext
Output Modalitiestext
LicenseLlama 3.1 Community License
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 73.1 % 2024-08-12 5-shot view
HUMANEVAL 67.1 pass@1 2024-08-12 — view
GSM8K 72.9 % 2024-08-12 0-shot CoT view
MATH 25.5 % 2024-08-12 0-shot CoT view
BBH 62.6 % 2024-08-12 3-shot CoT view
GPQA 31.5 % 2024-08-12 0-shot view
IFEVAL 60.7 % 2024-08-12 prompt_strict view
ARC 88.7 % 2024-08-12 challenge view
MUSR 38 % 2024-08-12 0-shot view
WINOGRANDE 78.1 % 2024-08-12 0-shot view

Pricing

Tier Price Currency
Input$0.18 / MtokUSD
Output$0.18 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-08-12

Compliance

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

Hermes 3 Llama 3.1 8B

Model Overview

NousResearch Hermes 3 Llama 3.1 8B 微调模型, 131K 上下文, 经济型开源模型, 适合本地部署。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other hermes-3-llama-3-1-8b 2024-08-12 131K text text Llama 3.1 Community License

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 73.1 % 5-shot
HumanEval 67.1 pass@1 —
GSM8K (Grade School Math 8K) 72.9 % 0-shot CoT
MATH 25.5 % 0-shot CoT
BBH (BIG-Bench Hard) 62.6 % 3-shot CoT
GPQA 31.5 % 0-shot
IFEval 60.7 % prompt_strict
ARC 88.7 % challenge
MUSR 38.0 % 0-shot
WinoGrande 78.1 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • Proprietary, not self-hostable.

Use Cases

  • General chat and Q&A

References