Nous Hermes 2 Yi 34B: Complete Benchmark Performance Guide

other nous-hermes-2-yi-34b 2024-01-22 Apache 2.0

In-depth analysis of Nous Hermes 2 Yi 34B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionnous-hermes-2-yi-34b
Release Date2024-01-22
Context Window4096 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU76.9%2024-01-225-shotview
HUMANEVAL73.2pass@12024-01-22—view
GSM8K82.7%2024-01-220-shot CoTview
MATH44.9%2024-01-220-shot CoTview
BBH75.6%2024-01-223-shot CoTview
GPQA39%2024-01-220-shotview
IFEVAL68.3%2024-01-22prompt_strictview
ARC93.4%2024-01-22challengeview
MUSR48.8%2024-01-220-shotview
WINOGRANDE83.4%2024-01-220-shotview

Pricing

TierPriceCurrency
Input$0.4 / MtokUSD
Output$0.4 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-01-22

Compliance

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

Nous Hermes 2 Yi 34B

Model Overview

NousResearch Hermes 2 Yi 34B 微调模型, 4K 上下文, 基于 Yi 34B, 改进多语言与指令遵循。

Core Specifications

VendorVersionRelease DateContext WindowInput ModalitiesOutput ModalitiesLicense
Othernous-hermes-2-yi-34b2024-01-224KtexttextApache 2.0

Benchmark Performance

BenchmarkScoreUnitNotes
MMLU (Massive Multitask Language Understanding)76.9%5-shot
HumanEval73.2pass@1—
GSM8K (Grade School Math 8K)82.7%0-shot CoT
MATH44.9%0-shot CoT
BBH (BIG-Bench Hard)75.6%3-shot CoT
GPQA39.0%0-shot
IFEval68.3%prompt_strict
ARC93.4%challenge
MUSR48.8%0-shot
WinoGrande83.4%0-shot

Pricing

InputOutputCache ReadCache Write
————

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • Proprietary, not self-hostable.
  • Context window 4K is limited.

Use Cases

  • Code generation and debugging

References