Open-Platypus: Complete Benchmark Performance Guide

other open-platypus 2023-09-15 MIT

In-depth analysis of Open-Platypus performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionopen-platypus
Release Date2023-09-15
Context Window2048 tokens
Input Modalitiestext
Output Modalitiestext
LicenseMIT
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 68.7 % 2023-09-15 5-shot view
HUMANEVAL 48.2 pass@1 2023-09-15 — view
GSM8K 43.9 % 2023-09-15 0-shot CoT view
MATH 21 % 2023-09-15 0-shot CoT view
BBH 63.7 % 2023-09-15 3-shot CoT view
GPQA 34.9 % 2023-09-15 0-shot view
IFEVAL 46 % 2023-09-15 prompt_strict view
ARC 80.1 % 2023-09-15 challenge view
MUSR 40 % 2023-09-15 0-shot view
WINOGRANDE 66.7 % 2023-09-15 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 2023-09-15

Compliance

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

Open-Platypus

Model Overview

Garage bAInd Open-Platypus 数据集与模型, 2K 上下文, 基于 Llama 2 微调, 适合 STEM 推理任务。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other open-platypus 2023-09-15 2K text text MIT

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 68.7 % 5-shot
HumanEval 48.2 pass@1 —
GSM8K (Grade School Math 8K) 43.9 % 0-shot CoT
MATH 21.0 % 0-shot CoT
BBH (BIG-Bench Hard) 63.7 % 3-shot CoT
GPQA 34.9 % 0-shot
IFEval 46.0 % prompt_strict
ARC 80.1 % challenge
MUSR 40.0 % 0-shot
WinoGrande 66.7 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • HumanEval 48.2, coding weak.
  • Proprietary, not self-hostable.
  • Context window 2K is limited.

Use Cases

  • General chat and Q&A

References