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

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU76.1%2024-05-135-shotview
HUMANEVAL74.5pass@12024-05-13—view
GSM8K82.6%2024-05-130-shot CoTview
MATH50.4%2024-05-130-shot CoTview
BBH74.1%2024-05-133-shot CoTview
GPQA34.7%2024-05-130-shotview
IFEVAL79.3%2024-05-13prompt_strictview
ARC93.7%2024-05-13challengeview
MUSR51%2024-05-130-shotview
WINOGRANDE79.2%2024-05-130-shotview

Pricing

TierPriceCurrency
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

모델 개요

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。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Otheryi-1-5-34b2024-05-134KtexttextApache 2.0

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)76.1%5-shot
HumanEval74.5pass@1—
GSM8K (Grade School Math 8K)82.6%0-shot CoT
MATH50.4%0-shot CoT
BBH (BIG-Bench Hard)74.1%3-shot CoT
GPQA34.7%0-shot
IFEval79.3%prompt_strict
ARC93.7%challenge
MUSR51.0%0-shot
WinoGrande79.2%0-shot

가격

입력출력캐시 읽기캐시 쓰기
————

백만 토큰당

강점

  • 可靠的通用模型。

약점

  • 闭源专有模型，不支持自托管。
  • 上下文窗口 4K 偏小。

사용 사례

  • 代码生成与调试

참고문헌