Yi Large Turbo: Complete Benchmark Performance Guide

other yi-large-turbo 2024-07-24 Proprietary

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

Key Specifications

Vendorother
Versionyi-large-turbo
Release Date2024-07-24
Context Window16384 tokens
Input Modalitiestext
Output Modalitiestext
LicenseProprietary
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU84.4%2024-07-245-shotview
HUMANEVAL72.4pass@12024-07-24—view
GSM8K81%2024-07-240-shot CoTview
MATH42.2%2024-07-240-shot CoTview
BBH76.4%2024-07-243-shot CoTview
GPQA38.2%2024-07-240-shotview
IFEVAL70.7%2024-07-24prompt_strictview
ARC95.6%2024-07-24challengeview
MUSR63.7%2024-07-240-shotview
WINOGRANDE82.3%2024-07-240-shotview

Pricing

TierPriceCurrency
Input$2 / MtokUSD
Output$2 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-07-24

Compliance

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

Yi Large Turbo

Model Overview

01.AI Yi Large Turbo 经济型旗舰, 16K 上下文, 速度快成本低, 性能接近 Yi Large。

Core Specifications

VendorVersionRelease DateContext WindowInput ModalitiesOutput ModalitiesLicense
Otheryi-large-turbo2024-07-2416KtexttextProprietary

Benchmark Performance

BenchmarkScoreUnitNotes
MMLU (Massive Multitask Language Understanding)84.4%5-shot
HumanEval72.4pass@1—
GSM8K (Grade School Math 8K)81.0%0-shot CoT
MATH42.2%0-shot CoT
BBH (BIG-Bench Hard)76.4%3-shot CoT
GPQA38.2%0-shot
IFEval70.7%prompt_strict
ARC95.6%challenge
MUSR63.7%0-shot
WinoGrande82.3%0-shot

Pricing

InputOutputCache ReadCache Write
————

per million tokens

Strengths

  • MMLU score 84.4, strong knowledge reasoning.

Weaknesses

  • Proprietary, not self-hostable.
  • Context window 16K is limited.

Use Cases

  • Code generation and debugging
  • Agent workflows and tool use

References