Yi Large: Complete Benchmark Performance Guide

other yi-large 2024-05-13 Proprietary

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

Key Specifications

Vendorother
Versionyi-large
Release Date2024-05-13
Context Window32768 tokens
Input Modalitiestext
Output Modalitiestext
LicenseProprietary
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 82.8 % 2024-05-13 5-shot view
HUMANEVAL 72.2 pass@1 2024-05-13 — view
GSM8K 81.3 % 2024-05-13 0-shot CoT view
MATH 55.9 % 2024-05-13 0-shot CoT view
BBH 77.1 % 2024-05-13 3-shot CoT view
GPQA 35.2 % 2024-05-13 0-shot view
IFEVAL 73.4 % 2024-05-13 prompt_strict view
ARC 94.8 % 2024-05-13 challenge view
MUSR 59.4 % 2024-05-13 0-shot view
WINOGRANDE 84.1 % 2024-05-13 0-shot view

Pricing

Tier Price Currency
Input$3 / MtokUSD
Output$3 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-05-13

Compliance

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

Yi Large

Model Overview

01.AI Yi Large 旗舰闭源模型, 32K 上下文, 中英文能力突出, 在 LMSYS 排行榜上接近 GPT-4。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other yi-large 2024-05-13 32K text text Proprietary

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 82.8 % 5-shot
HumanEval 72.2 pass@1 —
GSM8K (Grade School Math 8K) 81.3 % 0-shot CoT
MATH 55.9 % 0-shot CoT
BBH (BIG-Bench Hard) 77.1 % 3-shot CoT
GPQA 35.2 % 0-shot
IFEval 73.4 % prompt_strict
ARC 94.8 % challenge
MUSR 59.4 % 0-shot
WinoGrande 84.1 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • MMLU score 82.8, strong knowledge reasoning.

Weaknesses

  • Proprietary, not self-hostable.

Use Cases

  • Code generation and debugging
  • Agent workflows and tool use

References