Embed English v3: Complete Benchmark Performance Guide

cohere embed-english-v3 2023-11-01 CC-BY-NC-4.0

In-depth analysis of Embed English v3 performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorcohere
Versionembed-english-v3
Release Date2023-11-01
Context Window512 tokens
Input Modalitiestext
Output Modalities—
LicenseCC-BY-NC-4.0
Documentationhttps://docs.cohere.com/docs

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 0 % 2023-11-01 embed model - not applicable view
HUMANEVAL 0 pass@1 2023-11-01 embed model - not applicable view
GSM8K 0 % 2023-11-01 embed model - not applicable view
MATH 0 % 2023-11-01 embed model - not applicable view
BBH 0 % 2023-11-01 embed model - not applicable view
GPQA 0 % 2023-11-01 embed model - not applicable view
IFEVAL 0 % 2023-11-01 embed model - not applicable view
ARC 0 % 2023-11-01 embed model - not applicable view
MUSR 0 % 2023-11-01 embed model - not applicable view
WINOGRANDE 0 % 2023-11-01 embed model - not applicable view

Pricing

Tier Price Currency
Input$0.1 / MtokUSD
Output$0.1 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://cohere.com/pricing · as of 2023-11-01

Compliance

  • Data Residency: US
  • SOC2: ✓
  • HIPAA: ✗
  • GDPR: ✓
  • ISO 27001: ✓

Embed English v3

Model Overview

Cohere Embed English v3 英文嵌入模型, 512 token 输入, 为检索/分类/聚类优化, 英文语义搜索领先。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Cohere embed-english-v3 2023-11-01 512 text — CC-BY-NC-4.0

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 0.0 % embed model - not applicable
HumanEval 0.0 pass@1 embed model - not applicable
GSM8K (Grade School Math 8K) 0.0 % embed model - not applicable
MATH 0.0 % embed model - not applicable
BBH (BIG-Bench Hard) 0.0 % embed model - not applicable
GPQA 0.0 % embed model - not applicable
IFEval 0.0 % embed model - not applicable
ARC 0.0 % embed model - not applicable
MUSR 0.0 % embed model - not applicable
WinoGrande 0.0 % embed model - not applicable

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • MMLU 0.0, weak knowledge reasoning.
  • HumanEval 0.0, coding weak.
  • Proprietary, not self-hostable.
  • Context window 0K is limited.

Use Cases

  • General chat and Q&A

References