Yi 1.5 34B: Complete Benchmark Performance Guide

other yi-1-5-34b 2024-05-13 Apache 2.0

In-depth analysis of Yi 1.5 34B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionyi-1-5-34b
Release Date2024-05-13
Context Window4096 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 76.1 % 2024-05-13 5-shot view
HUMANEVAL 74.5 pass@1 2024-05-13 — view
GSM8K 82.6 % 2024-05-13 0-shot CoT view
MATH 50.4 % 2024-05-13 0-shot CoT view
BBH 74.1 % 2024-05-13 3-shot CoT view
GPQA 34.7 % 2024-05-13 0-shot view
IFEVAL 79.3 % 2024-05-13 prompt_strict view
ARC 93.7 % 2024-05-13 challenge view
MUSR 51 % 2024-05-13 0-shot view
WINOGRANDE 79.2 % 2024-05-13 0-shot view

Pricing

Tier Price Currency
Input$0.4 / MtokUSD
Output$0.4 / 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 1.5 34B

Model Overview

01.AI Yi 1.5 34B 开源模型, 4K 上下文, 中英文能力突出, 在 34B 规模上推理能力领先。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other yi-1-5-34b 2024-05-13 4K text text Apache 2.0

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 76.1 % 5-shot
HumanEval 74.5 pass@1 —
GSM8K (Grade School Math 8K) 82.6 % 0-shot CoT
MATH 50.4 % 0-shot CoT
BBH (BIG-Bench Hard) 74.1 % 3-shot CoT
GPQA 34.7 % 0-shot
IFEval 79.3 % prompt_strict
ARC 93.7 % challenge
MUSR 51.0 % 0-shot
WinoGrande 79.2 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • Proprietary, not self-hostable.
  • Context window 4K is limited.

Use Cases

  • Code generation and debugging

References