DeepSeek V2 Chat: Complete Benchmark Performance Guide

deepseek v2-chat 2024-06-17 DeepSeek License

In-depth analysis of DeepSeek V2 Chat performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendordeepseek
Versionv2-chat
Release Date2024-06-17
Context Window32768 tokens
Input Modalitiestext
Output Modalitiestext
LicenseDeepSeek License
Documentationhttps://api-docs.deepseek.com/

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU76.6%2024-06-175-shotview
HUMANEVAL67pass@12024-06-17—view
GSM8K77.4%2024-06-170-shot CoTview
MATH49.3%2024-06-170-shot CoTview
BBH75.4%2024-06-173-shot CoTview
GPQA38.3%2024-06-170-shotview
IFEVAL71.5%2024-06-17prompt_strictview
ARC94.6%2024-06-17challengeview
MUSR52%2024-06-170-shotview
WINOGRANDE80.2%2024-06-170-shotview

Pricing

TierPriceCurrency
Input$0.14 / MtokUSD
Output$0.28 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://api-docs.deepseek.com/quick_start/pricing · as of 2024-06-17

Compliance

  • Data Residency: CN
  • SOC2: ✗
  • HIPAA: ✗
  • GDPR: ✗
  • ISO 27001: ✗

DeepSeek V2 Chat

모델 개요

DeepSeek V2 Chat 对话版本, 32K 上下文, 针对对话场景优化, 适合聊天助手与客服应用。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Deepseekv2-chat2024-06-1732KtexttextDeepSeek License

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)76.6%5-shot
HumanEval67.0pass@1—
GSM8K (Grade School Math 8K)77.4%0-shot CoT
MATH49.3%0-shot CoT
BBH (BIG-Bench Hard)75.4%3-shot CoT
GPQA38.3%0-shot
IFEval71.5%prompt_strict
ARC94.6%challenge
MUSR52.0%0-shot
WinoGrande80.2%0-shot

가격

입력출력캐시 읽기캐시 쓰기
————

백만 토큰당

강점

  • 采用 MoE 混合专家架构。

약점

  • 闭源专有模型，不支持自托管。

사용 사례

  • 通用对话与问答

참고문헌