OpenChat 3.6 8B: Complete Benchmark Performance Guide

other openchat-3-6-8b 2024-05-21 Apache 2.0

In-depth analysis of OpenChat 3.6 8B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionopenchat-3-6-8b
Release Date2024-05-21
Context Window8192 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 69.2 % 2024-05-21 5-shot view
HUMANEVAL 61.5 pass@1 2024-05-21 — view
GSM8K 51.8 % 2024-05-21 0-shot CoT view
MATH 33.7 % 2024-05-21 0-shot CoT view
BBH 71 % 2024-05-21 3-shot CoT view
GPQA 30.3 % 2024-05-21 0-shot view
IFEVAL 56.7 % 2024-05-21 prompt_strict view
ARC 89.2 % 2024-05-21 challenge view
MUSR 38.2 % 2024-05-21 0-shot view
WINOGRANDE 74.5 % 2024-05-21 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 2024-05-21

Compliance

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

OpenChat 3.6 8B

Model Overview

OpenChat 3.6 8B 对话模型, 8K 上下文, 基于 Llama 3 8B 微调, 改进推理与编码能力。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other openchat-3-6-8b 2024-05-21 8K text text Apache 2.0

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 69.2 % 5-shot
HumanEval 61.5 pass@1 —
GSM8K (Grade School Math 8K) 51.8 % 0-shot CoT
MATH 33.7 % 0-shot CoT
BBH (BIG-Bench Hard) 71.0 % 3-shot CoT
GPQA 30.3 % 0-shot
IFEval 56.7 % prompt_strict
ARC 89.2 % challenge
MUSR 38.2 % 0-shot
WinoGrande 74.5 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • Proprietary, not self-hostable.
  • Context window 8K is limited.

Use Cases

  • General chat and Q&A

References