Yi 6B: Complete Benchmark Performance Guide

other yi-6b 2023-11-05 Apache 2.0

In-depth analysis of Yi 6B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionyi-6b
Release Date2023-11-05
Context Window4096 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 68 % 2023-11-05 5-shot view
HUMANEVAL 42.3 pass@1 2023-11-05 — view
GSM8K 37 % 2023-11-05 0-shot CoT view
MATH 29.9 % 2023-11-05 0-shot CoT view
BBH 55.3 % 2023-11-05 3-shot CoT view
GPQA 26.3 % 2023-11-05 0-shot view
IFEVAL 54.9 % 2023-11-05 prompt_strict view
ARC 88.4 % 2023-11-05 challenge view
MUSR 29.5 % 2023-11-05 0-shot view
WINOGRANDE 72.2 % 2023-11-05 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 2023-11-05

Compliance

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

Yi 6B

Model Overview

01.AI Yi 6B 经济型首代模型, 4K 上下文, 6B 参数, 适合本地部署与研究用途。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other yi-6b 2023-11-05 4K text text Apache 2.0

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 68.0 % 5-shot
HumanEval 42.3 pass@1 —
GSM8K (Grade School Math 8K) 37.0 % 0-shot CoT
MATH 29.9 % 0-shot CoT
BBH (BIG-Bench Hard) 55.3 % 3-shot CoT
GPQA 26.3 % 0-shot
IFEval 54.9 % prompt_strict
ARC 88.4 % challenge
MUSR 29.5 % 0-shot
WinoGrande 72.2 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • HumanEval 42.3, coding weak.
  • Proprietary, not self-hostable.
  • Context window 4K is limited.

Use Cases

  • General chat and Q&A

References